tirana-survey-bert-clinical
Query: BERT clinical text classification Indonesian
Results: 50
Date: 2026-07-08T07:35:19.806Z
1. Publicly Available Clinical BERT Embeddings
Authors: Emily Alsentzer, John R. Murphy, Willie Boag, Wei-Hung Weng, Di Jin, Tristan Naumann, Matthew B. A. McDermott
Categories: cs.CL
Published: 2019-04-06
arXiv: 1904.03323v3
Abstract:
Contextual word embedding models such as ELMo (Peters et al., 2018) and BERT (Devlin et al., 2018) have dramatically improved performance for many natural language processing (NLP) tasks in recent months. However, these models have been minimally explored on specialty corpora, such as clinical text; moreover, in the clinical domain, no publicly-available pre-trained BERT models yet exist. In this work, we address this need by exploring and releasing BERT models for clinical text: one for generic clinical text and another for discharge summaries specifically. We demonstrate that using a domain-specific model yields performance improvements on three common clinical NLP tasks as compared to nonspecific embeddings. These domain-specific models are not as performant on two clinical de-identification tasks, and argue that this is a natural consequence of the differences between de-identified source text and synthetically non de-identified task text.
2. Exploring Text Specific and Blackbox Fairness Algorithms in Multimodal Clinical NLP
Authors: John Chen, Ian Berlot-Attwell, Safwan Hossain, Xindi Wang, Frank Rudzicz
Categories: cs.CL, cs.AI
Published: 2020-11-19
arXiv: 2011.09625v2
Abstract:
Clinical machine learning is increasingly multimodal, collected in both structured tabular formats and unstructured forms such as freetext. We propose a novel task of exploring fairness on a multimodal clinical dataset, adopting equalized odds for the downstream medical prediction tasks. To this end, we investigate a modality-agnostic fairness algorithm - equalized odds post processing - and compare it to a text-specific fairness algorithm: debiased clinical word embeddings. Despite the fact that debiased word embeddings do not explicitly address equalized odds of protected groups, we show that a text-specific approach to fairness may simultaneously achieve a good balance of performance and classical notions of fairness. We hope that our paper inspires future contributions at the critical intersection of clinical NLP and fairness. The full source code is available here: https://github.com/johntiger1/multimodal_fairness
3. Multilingual Clinical NER for Diseases and Medications Recognition in Cardiology Texts using BERT Embeddings
Authors: Manuela Daniela Danu, George Marica, Constantin Suciu, Lucian Mihai Itu, Oladimeji Farri
Categories: cs.CL
Published: 2025-10-20
arXiv: 2510.17437v1
Abstract:
The rapidly increasing volume of electronic health record (EHR) data underscores a pressing need to unlock biomedical knowledge from unstructured clinical texts to support advancements in data-driven clinical systems, including patient diagnosis, disease progression monitoring, treatment effects assessment, prediction of future clinical events, etc. While contextualized language models have demonstrated impressive performance improvements for named entity recognition (NER) systems in English corpora, there remains a scarcity of research focused on clinical texts in low-resource languages. To bridge this gap, our study aims to develop multiple deep contextual embedding models to enhance clinical NER in the cardiology domain, as part of the BioASQ MultiCardioNER shared task. We explore the effectiveness of different monolingual and multilingual BERT-based models, trained on general domain text, for extracting disease and medication mentions from clinical case reports written in English, Spanish, and Italian. We achieved an F1-score of 77.88% on Spanish Diseases Recognition (SDR), 92.09% on Spanish Medications Recognition (SMR), 91.74% on English Medications Recognition (EMR), and 88.9% on Italian Medications Recognition (IMR). These results outperform the mean and median F1 scores in the test leaderboard across all subtasks, with the mean/median values being: 69.61%/75.66% for SDR, 81.22%/90.18% for SMR, 89.2%/88.96% for EMR, and 82.8%/87.76% for IMR.
4. From Generative Modeling to Clinical Classification: A GPT-Based Architecture for EHR Notes
Authors: Fariba Afrin Irany, Sampson Akwafuo
Categories: cs.CL
Published: 2026-01-29
arXiv: 2601.21955v3
Abstract:
The increasing availability of unstructured clinical narratives in electronic health records (EHRs) has created new opportunities for automated disease characterization, cohort identification, and clinical decision support. However, modeling long, domain-specific clinical text remains challenging due to limited labeled data, severe class imbalance, and the high computational cost of adapting large pretrained language models. This study presents a GPT-based architecture for clinical text classification that adapts a pretrained decoder-only Transformer using a selective fine-tuning strategy. Rather than updating all model parameters, the majority of the GPT-2 backbone is frozen, and training is restricted to the final Transformer block, the final layer normalization, and a lightweight classification head. This approach substantially reduces the number of trainable parameters while preserving the representational capacity required to model complex clinical language. The proposed method is evaluated on radiology reports from the MIMIC-IV-Note dataset using uncertainty-aware CheXpert-style labels derived directly from report text. Experiments cover multiple problem formulations, including multi-label classification of radiographic findings, binary per-label classification under different uncertainty assumptions, and aggregate disease outcome prediction. Across varying dataset sizes, the model exhibits stable convergence behavior and strong classification performance, particularly in settings dominated by non-mention and negated findings. Overall, the results indicate that selective fine-tuning of pretrained generative language models provides an efficient and effective pathway for clinical text classification, enabling scalable adaptation to real-world EHR data while significantly reducing computational complexity.
5. Lightweight Transformers for Clinical Natural Language Processing
Authors: Omid Rohanian, Mohammadmahdi Nouriborji, Hannah Jauncey, Samaneh Kouchaki, ISARIC Clinical Characterisation Group, Lei Clifton, Laura Merson, David A. Clifton
Categories: cs.CL, cs.AI, cs.LG
Published: 2023-02-09
arXiv: 2302.04725v1
Abstract:
Specialised pre-trained language models are becoming more frequent in NLP since they can potentially outperform models trained on generic texts. BioBERT and BioClinicalBERT are two examples of such models that have shown promise in medical NLP tasks. Many of these models are overparametrised and resource-intensive, but thanks to techniques like Knowledge Distillation (KD), it is possible to create smaller versions that perform almost as well as their larger counterparts. In this work, we specifically focus on development of compact language models for processing clinical texts (i.e. progress notes, discharge summaries etc). We developed a number of efficient lightweight clinical transformers using knowledge distillation and continual learning, with the number of parameters ranging from 15 million to 65 million. These models performed comparably to larger models such as BioBERT and ClinicalBioBERT and significantly outperformed other compact models trained on general or biomedical data. Our extensive evaluation was done across several standard datasets and covered a wide range of clinical text-mining tasks, including Natural Language Inference, Relation Extraction, Named Entity Recognition, and Sequence Classification. To our knowledge, this is the first comprehensive study specifically focused on creating efficient and compact transformers for clinical NLP tasks. The models and code used in this study can be found on our Huggingface profile at https://huggingface.co/nlpie and Github page at https://github.com/nlpie-research/Lightweight-Clinical-Transformers, respectively, promoting reproducibility of our results.
6. Improving Indonesian Text Classification Using Multilingual Language Model
Authors: Ilham Firdausi Putra, Ayu Purwarianti
Categories: cs.CL, cs.AI
Published: 2020-09-12
arXiv: 2009.05713v1
Abstract:
Compared to English, the amount of labeled data for Indonesian text classification tasks is very small. Recently developed multilingual language models have shown its ability to create multilingual representations effectively. This paper investigates the effect of combining English and Indonesian data on building Indonesian text classification (e.g., sentiment analysis and hate speech) using multilingual language models. Using the feature-based approach, we observe its performance on various data sizes and total added English data. The experiment showed that the addition of English data, especially if the amount of Indonesian data is small, improves performance. Using the fine-tuning approach, we further showed its effectiveness in utilizing the English language to build Indonesian text classification models.
7. Using Bottleneck Adapters to Identify Cancer in Clinical Notes under Low-Resource Constraints
Authors: Omid Rohanian, Hannah Jauncey, Mohammadmahdi Nouriborji, Vinod Kumar Chauhan, Bronner P. Gonçalves, Christiana Kartsonaki, ISARIC Clinical Characterisation Group, Laura Merson, David Clifton
Categories: cs.CL, cs.AI
Published: 2022-10-17
arXiv: 2210.09440v2
Abstract:
Processing information locked within clinical health records is a challenging task that remains an active area of research in biomedical NLP. In this work, we evaluate a broad set of machine learning techniques ranging from simple RNNs to specialised transformers such as BioBERT on a dataset containing clinical notes along with a set of annotations indicating whether a sample is cancer-related or not. Furthermore, we specifically employ efficient fine-tuning methods from NLP, namely, bottleneck adapters and prompt tuning, to adapt the models to our specialised task. Our evaluations suggest that fine-tuning a frozen BERT model pre-trained on natural language and with bottleneck adapters outperforms all other strategies, including full fine-tuning of the specialised BioBERT model. Based on our findings, we suggest that using bottleneck adapters in low-resource situations with limited access to labelled data or processing capacity could be a viable strategy in biomedical text mining. The code used in the experiments are going to be made available at https://github.com/omidrohanian/bottleneck-adapters.
8. Domain Adaptation of the Pyannote Diarization Pipeline for Conversational Indonesian Audio
Authors: Muhammad Daffa’i Rafi Prasetyo, Ramadhan Andika Putra, Zaidan Naufal Ilmi, Kurniawati Azizah
Categories: cs.SD
Published: 2026-01-07
arXiv: 2601.03684v1
Abstract:
This study presents a domain adaptation approach for speaker diarization targeting conversational Indonesian audio. We address the challenge of adapting an English-centric diarization pipeline to a low-resource language by employing synthetic data generation using neural Text-to-Speech technology. Experiments were conducted with varying training configurations, a small dataset (171 samples) and a large dataset containing 25 hours of synthetic speech. Results demonstrate that the baseline \texttt{pyannote/segmentation-3.0} model, trained on the AMI Corpus, achieves a Diarization Error Rate (DER) of 53.47% when applied zero-shot to Indonesian. Domain adaptation significantly improves performance, with the small dataset models reducing DER to 34.31% (1 epoch) and 34.81% (2 epochs). The model trained on the 25-hour dataset achieves the best performance with a DER of 29.24%, representing a 13.68% absolute improvement over the baseline while maintaining 99.06% Recall and 87.14% F1-Score.
9. Suryakala-Nusantara: Documenting Indonesian Sundials
Authors: Rhorom Priyatikanto
Categories: physics.pop-ph, astro-ph.IM
Published: 2013-12-10
arXiv: 1312.2742v1
Abstract:
Sundial is the ancient or classic timekeeper device, especially prior to the invention of mechanical clock. In the classical Islamic civilization, the daily movement of the Sun becomes main indicator of praying time, which can be deduced using sundial. This kind of device probably permeated to Indonesia during the Islamic acculturation. Since then, the development of astronomical knowledge, technology, art and architectural in classical Indonesia are partially reflected into sundial. These historical attractions of sundial demand comprehensive documentation and investigation of Indonesian sundial which are rarely found in the current literatures. The required spatial and temporal information regarding Indonesian sundial can be collected by general public through citizen science scheme. This concept may answer scientific curiosity of a research and also educate the people, expose them with science. In this article, general scheme of citizen science are discussed, its application for sundial study in Indonesia is proposed as Suryakala-Nusantara program.
10. Hybrid TF–IDF Logistic Regression and MLP Neural Baseline for Indonesian Three-Class Sentiment Analysis on Social Media Text
Authors: Allya Nurul Islami Pasha, Eka Fidiya Putri, Luluk Muthoharoh, Ardika Satria, Martin C. T. Manullang
Categories: cs.CL
Published: 2026-05-08
arXiv: 2605.07793v1
Abstract:
This paper presents a compact three-class sentiment analysis study for Indonesian social media text. The task is formulated with positive, negative, and neutral outputs derived from a fine-grained emotion dataset. The proposed practical baseline combines TF–IDF text features, three lightweight numeric metadata features, and a balanced multinomial Logistic Regression classifier. For comparison, the study also includes a neural baseline using a two-layer multilayer perceptron (MLP) over the same hybrid feature representation. The dataset originally contains 732 rows and 191 fine-grained emotion labels; after cleaning, deduplication, and label remapping, 707 samples remain with an imbalanced distribution of 459 positive, 188 negative, and 60 neutral instances. Experimental results show that the Logistic Regression deployment model reaches 0.8028 accuracy, 0.8003 weighted F1, and 0.7276 macro F1, while project documentation reports a higher-accuracy but non-production MLP baseline. These findings indicate that careful preprocessing, interpretable feature engineering, and class balancing remain competitive for small Indonesian sentiment datasets, whereas the neural baseline is better treated as a comparative experiment than as the default deployment model.
11. Multiple Sclerosis Severity Classification From Clinical Text
Authors: Alister D Costa, Stefan Denkovski, Michal Malyska, Sae Young Moon, Brandon Rufino, Zhen Yang, Taylor Killian, Marzyeh Ghassemi
Categories: cs.CL, cs.LG
Published: 2020-10-29
arXiv: 2010.15316v1
Abstract:
Multiple Sclerosis (MS) is a chronic, inflammatory and degenerative neurological disease, which is monitored by a specialist using the Expanded Disability Status Scale (EDSS) and recorded in unstructured text in the form of a neurology consult note. An EDSS measurement contains an overall “EDSS” score and several functional subscores. Typically, expert knowledge is required to interpret consult notes and generate these scores. Previous approaches used limited context length Word2Vec embeddings and keyword searches to predict scores given a consult note, but often failed when scores were not explicitly stated. In this work, we present MS-BERT, the first publicly available transformer model trained on real clinical data other than MIMIC. Next, we present MSBC, a classifier that applies MS-BERT to generate embeddings and predict EDSS and functional subscores. Lastly, we explore combining MSBC with other models through the use of Snorkel to generate scores for unlabelled consult notes. MSBC achieves state-of-the-art performance on all metrics and prediction tasks and outperforms the models generated from the Snorkel ensemble. We improve Macro-F1 by 0.12 (to 0.88) for predicting EDSS and on average by 0.29 (to 0.63) for predicting functional subscores over previous Word2Vec CNN and rule-based approaches.
12. Comparative Analysis of AutoML and BiLSTM Models for Cyberbullying Detection on Indonesian Instagram Comments
Authors: Raihana Adelia Putri, Aisyah Musfirah, Anggi Puspita Ningrum, Luluk Muthoharoh, Ardika Satria, Martin Clinton Tosima Manullang
Categories: cs.CL
Published: 2026-04-29
arXiv: 2604.26229v1
Abstract:
This study compares machine learning and deep learning approaches for cyberbullying detection in Indonesian-language Instagram comments. Using a balanced dataset of 650 comments labeled as Bullying and Non-Bullying, the study evaluates Naive Bayes, Logistic Regression, and Support Vector Machine with TF-IDF features, as well as BiLSTM and BiLSTM with Bahdanau Attention. A preprocessing pipeline tailored to informal Indonesian text is applied, including slang normalization, stopword removal, and stemming. The results show that Logistic Regression performs best among the machine learning models, while BiLSTM with Attention achieves the strongest overall deep learning performance. The findings highlight the value of domain-specific preprocessing and show that although deep learning captures contextual patterns more effectively, machine learning remains a competitive option for resource-constrained deployments.
13. Short Text Classification via Term Graph
Authors: Wei Pang
Categories: cs.IR, cs.LG, stat.ML
Published: 2020-01-20
arXiv: 2001.10338v1
Abstract:
Short text classi cation is a method for classifying short sentence with prede ned labels. However, short text is limited in shortness in text length that leads to a challenging problem of sparse features. Most of existing methods treat each short sentences as independently and identically distributed (IID), local context only in the sentence itself is focused and the relational information between sentences are lost. To overcome these limitations, we propose a PathWalk model that combine the strength of graph networks and short sentences to solve the sparseness of short text. Experimental results on four different available datasets show that our PathWalk method achieves the state-of-the-art results, demonstrating the efficiency and robustness of graph networks for short text classification.
14. VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification
Authors: Zhibin Lu, Pan Du, Jian-Yun Nie
Categories: cs.CL, cs.LG, stat.ML
Published: 2020-04-12
arXiv: 2004.05707v1
Abstract:
Much progress has been made recently on text classification with methods based on neural networks. In particular, models using attention mechanism such as BERT have shown to have the capability of capturing the contextual information within a sentence or document. However, their ability of capturing the global information about the vocabulary of a language is more limited. This latter is the strength of Graph Convolutional Networks (GCN). In this paper, we propose VGCN-BERT model which combines the capability of BERT with a Vocabulary Graph Convolutional Network (VGCN). Local information and global information interact through different layers of BERT, allowing them to influence mutually and to build together a final representation for classification. In our experiments on several text classification datasets, our approach outperforms BERT and GCN alone, and achieve higher effectiveness than that reported in previous studies.
15. Indonesian Text-to-Image Synthesis with Sentence-BERT and FastGAN
Authors: Made Raharja Surya Mahadi, Nugraha Priya Utama
Categories: cs.CV
Published: 2023-03-25
arXiv: 2303.14517v1
Abstract:
Currently, text-to-image synthesis uses text encoder and image generator architecture. Research on this topic is challenging. This is because of the domain gap between natural language and vision. Nowadays, most research on this topic only focuses on producing a photo-realistic image, but the other domain, in this case, is the language, which is less concentrated. A lot of the current research uses English as the input text. Besides, there are many languages around the world. Bahasa Indonesia, as the official language of Indonesia, is quite popular. This language has been taught in Philipines, Australia, and Japan. Translating or recreating a new dataset into another language with good quality will cost a lot. Research on this domain is necessary because we need to examine how the image generator performs in other languages besides generating photo-realistic images. To achieve this, we translate the CUB dataset into Bahasa using google translate and manually by humans. We use Sentence BERT as the text encoder and FastGAN as the image generator. FastGAN uses lots of skip excitation modules and auto-encoder to generate an image with resolution 512x512x3, which is twice as bigger as the current state-of-the-art model (Zhang, Xu, Li, Zhang, Wang, Huang and Metaxas, 2019). We also get 4.76 +- 0.43 and 46.401 on Inception Score and Fréchet inception distance, respectively, and comparable with the current English text-to-image generation models. The mean opinion score also gives as 3.22 out of 5, which means the generated image is acceptable by humans. Link to source code: https://github.com/share424/Indonesian-Text-to-Image-synthesis-with-Sentence-BERT-and-FastGAN
16. IndoBERT-Sentiment: Context-Conditioned Sentiment Classification for Indonesian Text
Authors: Muhammad Apriandito Arya Saputra, Andry Alamsyah, Dian Puteri Ramadhani, Thomhert Suprapto Siadari, Hanif Fakhrurroja
Categories: cs.CL
Published: 2026-04-08
arXiv: 2604.07057v1
Abstract:
Existing Indonesian sentiment analysis models classify text in isolation, ignoring the topical context that often determines whether a statement is positive, negative, or neutral. We introduce IndoBERT-Sentiment, a context-conditioned sentiment classifier that takes both a topical context and a text as input, producing sentiment predictions grounded in the topic being discussed. Built on IndoBERT Large (335M parameters) and trained on 31,360 context-text pairs labeled across 188 topics, the model achieves an F1 macro of 0.856 and accuracy of 88.1%. In a head-to-head evaluation against three widely used general-purpose Indonesian sentiment models on the same test set, IndoBERT-Sentiment outperforms the best baseline by 35.6 F1 points. We show that context-conditioning, previously demonstrated for relevancy classification, transfers effectively to sentiment analysis and enables the model to correctly classify texts that are systematically misclassified by context-free approaches.
17. KG-MTT-BERT: Knowledge Graph Enhanced BERT for Multi-Type Medical Text Classification
Authors: Yong He, Cheng Wang, Shun Zhang, Nan Li, Zhaorong Li, Zhenyu Zeng
Categories: cs.CL, cs.AI, cs.LG
Published: 2022-10-08
arXiv: 2210.03970v1
Abstract:
Medical text learning has recently emerged as a promising area to improve healthcare due to the wide adoption of electronic health record (EHR) systems. The complexity of the medical text such as diverse length, mixed text types, and full of medical jargon, poses a great challenge for developing effective deep learning models. BERT has presented state-of-the-art results in many NLP tasks, such as text classification and question answering. However, the standalone BERT model cannot deal with the complexity of the medical text, especially the lengthy clinical notes. Herein, we develop a new model called KG-MTT-BERT (Knowledge Graph Enhanced Multi-Type Text BERT) by extending the BERT model for long and multi-type text with the integration of the medical knowledge graph. Our model can outperform all baselines and other state-of-the-art models in diagnosis-related group (DRG) classification, which requires comprehensive medical text for accurate classification. We also demonstrated that our model can effectively handle multi-type text and the integration of medical knowledge graph can significantly improve the performance.
18. Emoji Prediction in Tweets using BERT
Authors: Muhammad Osama Nusrat, Zeeshan Habib, Mehreen Alam, Saad Ahmed Jamal
Categories: cs.CL, cs.AI
Published: 2023-07-05
arXiv: 2307.02054v3
Abstract:
In recent years, the use of emojis in social media has increased dramatically, making them an important element in understanding online communication. However, predicting the meaning of emojis in a given text is a challenging task due to their ambiguous nature. In this study, we propose a transformer-based approach for emoji prediction using BERT, a widely-used pre-trained language model. We fine-tuned BERT on a large corpus of text (tweets) containing both text and emojis to predict the most appropriate emoji for a given text. Our experimental results demonstrate that our approach outperforms several state-of-the-art models in predicting emojis with an accuracy of over 75 percent. This work has potential applications in natural language processing, sentiment analysis, and social media marketing.
19. Benchmarking PyCaret AutoML Against IndoBERT Fine-Tuning for Sentiment Analysis on Indonesian IKN Twitter Data
Authors: Mutia Alfi Mayzaroh, Dwi Fitria Ningsih, Nindi Destriani, Martin C. T. Manullang
Categories: cs.CL
Published: 2026-04-28
arXiv: 2604.25392v1
Abstract:
This paper benchmarks a classical machine learning approach based on PyCaret AutoML against a deep learning approach based on IndoBERT fine-tuning for binary sentiment analysis of Indonesian-language Twitter comments related to Ibu Kota Nusantara (IKN). The dataset contains 1,472 manually labeled samples, consisting of 780 negative and 692 positive comments. In the machine learning setting, Logistic Regression, Naive Bayes, and Support Vector Machine were evaluated using 10-fold cross-validation, with Logistic Regression achieving the best performance among the classical models at 77.57% accuracy and 77.17% F1-score. In the deep learning setting, the indobenchmark/indobert-base-p1 model was fine-tuned for five epochs and achieved 89.59% test accuracy and 89.37% F1-score. The results show that IndoBERT substantially outperforms the machine learning baselines, highlighting the effectiveness of Transformer-based contextual representations for informal Indonesian social media text.
20. Sentiment Analysis of Indonesian Spotify Reviews Using Machine Learning and BiLSTM
Authors: Uliano Wilyam Purba, Andre Hadiman Rotua Parhusip, Sahid Maulana, Luluk Muthoharoh, Ardika Satria, Martin C. T. Manullang
Categories: cs.CL
Published: 2026-05-05
arXiv: 2605.03443v1
Abstract:
This paper benchmarks classical machine learning and deep learning approaches for three-class sentiment classification of Indonesian Spotify reviews. Using 100,000 scraped reviews and 70,155 cleaned samples, the study compares Support Vector Machine, Multinomial Naive Bayes, and Decision Tree models with a two-layer BiLSTM. Both approaches use the same preprocessing pipeline, including slang normalization, stopword removal, and stemming. Decision Tree achieves the best performance among the classical models, while BiLSTM attains the highest weighted F1-score overall but fails on the minority neutral class. The paper concludes that BiLSTM is stronger for overall sentiment detection, whereas machine learning with SMOTE provides more balanced three-class performance.
21. Benchmarking LightGBM and BiLSTM for Sentiment Analysis on Indonesian E-Commerce Reviews
Authors: Lidia Natasyah Marpaung, Vania Claresta, Iqfina Haula Halika, Luluk Muthoharoh, Ardika Satria, Martin Clinton Tosima Manullang
Categories: cs.CL
Published: 2026-05-02
arXiv: 2605.01322v1
Abstract:
This study presents a comparative analysis between two primary approaches in Natural Language Processing (NLP): Machine Learning (ML) utilizing the PyCaret AutoML framework, and Deep Learning (DL). The evaluation is conducted on a sentiment analysis task using an Indonesian e-commerce review dataset sourced from Hugging Face. The dataset, consisting of 15,000 samples, is partitioned into training, validation, and testing sets. The ML experiments compare LightGBM, Logistic Regression, and Support Vector Machine (SVM) algorithms, whereas the DL experiment implements a Bidirectional Long Short-Term Memory (BiLSTM) architecture. The experimental results demonstrate that the BiLSTM model outperforms all ML models, achieving an accuracy of 98.87% and an F1-Score of 98.87%. Meanwhile, LightGBM emerges as the best-performing ML model with an accuracy of 98.23% in a highly efficient training time. This research proves that the BiLSTM architecture is highly capable of capturing the sequential context of Indonesian review texts, making it the superior model for this specific classification task.
22. L2D-Clinical: Learning to Defer for Adaptive Model Selection in Clinical Text Classification
Authors: Rishik Kondadadi, John E. Ortega
Categories: cs.CL, cs.AI
Published: 2026-04-14
arXiv: 2604.13285v1
Abstract:
Clinical text classification requires choosing between specialized fine-tuned models (BERT variants) and general-purpose large language models (LLMs), yet neither dominates across all instances. We introduce Learning to Defer for clinical text (L2D-Clinical), a framework that learns when a BERT classifier should defer to an LLM based on uncertainty signals and text characteristics. Unlike prior L2D work that defers to human experts assumed universally superior, our approach enables adaptive deferral-improving accuracy when the LLM complements BERT. We evaluate on two English clinical tasks: (1) ADE detection (ADE Corpus V2), where BioBERT (F1=0.911) outperforms the LLM (F1=0.765), and (2) treatment outcome classification (MIMIC-IV with multi-LLM consensus ground truth), where GPT-5-nano (F1=0.967) outperforms ClinicalBERT (F1=0.887). On ADE, L2D-Clinical achieves F1=0.928 (+1.7 points over BERT) by selectively deferring 7% of instances where the LLM’s high recall compensates for BERT’s misses. On MIMIC, L2D-Clinical achieves F1=0.980 (+9.3 points over BERT) by deferring only 16.8% of cases to the LLM. The key insight is that L2D-Clinical learns to selectively leverage LLM strengths while minimizing API costs.
23. Clinical ModernBERT: An efficient and long context encoder for biomedical text
Authors: Simon A. Lee, Anthony Wu, Jeffrey N. Chiang
Categories: cs.CL, cs.AI, cs.LG
Published: 2025-04-04
arXiv: 2504.03964v1
Abstract:
We introduce Clinical ModernBERT, a transformer based encoder pretrained on large scale biomedical literature, clinical notes, and medical ontologies, incorporating PubMed abstracts, MIMIC IV clinical data, and medical codes with their textual descriptions. Building on ModernBERT the current state of the art natural language text encoder featuring architectural upgrades such as rotary positional embeddings (RoPE), Flash Attention, and extended context length up to 8,192 tokens our model adapts these innovations specifically for biomedical and clinical domains. Clinical ModernBERT excels at producing semantically rich representations tailored for long context tasks. We validate this both by analyzing its pretrained weights and through empirical evaluation on a comprehensive suite of clinical NLP benchmarks.
24. How to Fine-Tune BERT for Text Classification?
Authors: Chi Sun, Xipeng Qiu, Yige Xu, Xuanjing Huang
Categories: cs.CL
Published: 2019-05-14
arXiv: 1905.05583v3
Abstract:
Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing results in many language understanding tasks. In this paper, we conduct exhaustive experiments to investigate different fine-tuning methods of BERT on text classification task and provide a general solution for BERT fine-tuning. Finally, the proposed solution obtains new state-of-the-art results on eight widely-studied text classification datasets.
25. Indonesian-English Code-Switching Speech Synthesizer Utilizing Multilingual STEN-TTS and Bert LID
Authors: Ahmad Alfani Handoyo, Chung Tran, Dessi Puji Lestari, Sakriani Sakti
Categories: cs.CL, cs.AI, cs.SD, eess.AS
Published: 2024-12-26
arXiv: 2412.19043v1
Abstract:
Multilingual text-to-speech systems convert text into speech across multiple languages. In many cases, text sentences may contain segments in different languages, a phenomenon known as code-switching. This is particularly common in Indonesia, especially between Indonesian and English. Despite its significance, no research has yet developed a multilingual TTS system capable of handling code-switching between these two languages. This study addresses Indonesian-English code-switching in STEN-TTS. Key modifications include adding a language identification component to the text-to-phoneme conversion using finetuned BERT for per-word language identification, as well as removing language embedding from the base model. Experimental results demonstrate that the code-switching model achieves superior naturalness and improved speech intelligibility compared to the Indonesian and English baseline STEN-TTS models.
26. Fine-tuning Pretrained Multilingual BERT Model for Indonesian Aspect-based Sentiment Analysis
Authors: Annisa Nurul Azhar, Masayu Leylia Khodra
Categories: cs.CL
Published: 2021-03-05
arXiv: 2103.03732v1
Abstract:
Although previous research on Aspect-based Sentiment Analysis (ABSA) for Indonesian reviews in hotel domain has been conducted using CNN and XGBoost, its model did not generalize well in test data and high number of OOV words contributed to misclassification cases. Nowadays, most state-of-the-art results for wide array of NLP tasks are achieved by utilizing pretrained language representation. In this paper, we intend to incorporate one of the foremost language representation model, BERT, to perform ABSA in Indonesian reviews dataset. By combining multilingual BERT (m-BERT) with task transformation method, we manage to achieve significant improvement by 8% on the F1-score compared to the result from our previous study.
27. Dilated Convolutional Attention Network for Medical Code Assignment from Clinical Text
Authors: Shaoxiong Ji, Erik Cambria, Pekka Marttinen
Categories: cs.CL, cs.IR
Published: 2020-09-30
arXiv: 2009.14578v1
Abstract:
Medical code assignment, which predicts medical codes from clinical texts, is a fundamental task of intelligent medical information systems. The emergence of deep models in natural language processing has boosted the development of automatic assignment methods. However, recent advanced neural architectures with flat convolutions or multi-channel feature concatenation ignore the sequential causal constraint within a text sequence and may not learn meaningful clinical text representations, especially for lengthy clinical notes with long-term sequential dependency. This paper proposes a Dilated Convolutional Attention Network (DCAN), integrating dilated convolutions, residual connections, and label attention, for medical code assignment. It adopts dilated convolutions to capture complex medical patterns with a receptive field which increases exponentially with dilation size. Experiments on a real-world clinical dataset empirically show that our model improves the state of the art.
28. Arabic Synonym BERT-based Adversarial Examples for Text Classification
Authors: Norah Alshahrani, Saied Alshahrani, Esma Wali, Jeanna Matthews
Categories: cs.CL
Published: 2024-02-05
arXiv: 2402.03477v1
Abstract:
Text classification systems have been proven vulnerable to adversarial text examples, modified versions of the original text examples that are often unnoticed by human eyes, yet can force text classification models to alter their classification. Often, research works quantifying the impact of adversarial text attacks have been applied only to models trained in English. In this paper, we introduce the first word-level study of adversarial attacks in Arabic. Specifically, we use a synonym (word-level) attack using a Masked Language Modeling (MLM) task with a BERT model in a black-box setting to assess the robustness of the state-of-the-art text classification models to adversarial attacks in Arabic. To evaluate the grammatical and semantic similarities of the newly produced adversarial examples using our synonym BERT-based attack, we invite four human evaluators to assess and compare the produced adversarial examples with their original examples. We also study the transferability of these newly produced Arabic adversarial examples to various models and investigate the effectiveness of defense mechanisms against these adversarial examples on the BERT models. We find that fine-tuned BERT models were more susceptible to our synonym attacks than the other Deep Neural Networks (DNN) models like WordCNN and WordLSTM we trained. We also find that fine-tuned BERT models were more susceptible to transferred attacks. We, lastly, find that fine-tuned BERT models successfully regain at least 2% in accuracy after applying adversarial training as an initial defense mechanism.
29. MSVD-Indonesian: A Benchmark for Multimodal Video-Text Tasks in Indonesian
Authors: Willy Fitra Hendria
Categories: cs.MM, cs.CL, cs.CV, cs.LG, eess.IV
Published: 2023-06-20
arXiv: 2306.11341v2
Abstract:
Multimodal learning on video and text has seen significant progress, particularly in tasks like text-to-video retrieval, video-to-text retrieval, and video captioning. However, most existing methods and datasets focus exclusively on English. Despite Indonesian being one of the most widely spoken languages, multimodal research in Indonesian remains under-explored, largely due to the lack of benchmark datasets. To address this gap, we introduce the first public Indonesian video-text dataset by translating the English captions in the MSVD dataset into Indonesian. Using this dataset, we evaluate neural network models which were developed for the English video-text dataset on three tasks, i.e., text-to-video retrieval, video-to-text retrieval, and video captioning. Most existing models rely on feature extractors pretrained on English vision-language datasets, raising concerns about their applicability to Indonesian, given the scarcity of large-scale pretraining resources in the language. We apply a cross-lingual transfer learning approach by leveraging English-pretrained extractors and fine-tuning models on our Indonesian dataset. Experimental results demonstrate that this strategy improves performance across all tasks and metrics. We release our dataset publicly to support future research and hope it will inspire further progress in Indonesian multimodal learning.
30. BERT Fine-Tuning for Sentiment Analysis on Indonesian Mobile Apps Reviews
Authors: Kuncahyo Setyo Nugroho, Anantha Yullian Sukmadewa, Haftittah Wuswilahaken DW, Fitra Abdurrachman Bachtiar, Novanto Yudistira
Categories: cs.CL, cs.LG
Published: 2021-07-14
arXiv: 2107.06802v1
Abstract:
User reviews have an essential role in the success of the developed mobile apps. User reviews in the textual form are unstructured data, creating a very high complexity when processed for sentiment analysis. Previous approaches that have been used often ignore the context of reviews. In addition, the relatively small data makes the model overfitting. A new approach, BERT, has been introduced as a transfer learning model with a pre-trained model that has previously been trained to have a better context representation. This study examines the effectiveness of fine-tuning BERT for sentiment analysis using two different pre-trained models. Besides the multilingual pre-trained model, we use the pre-trained model that only has been trained in Indonesian. The dataset used is Indonesian user reviews of the ten best apps in 2020 in Google Play sites. We also perform hyper-parameter tuning to find the optimum trained model. Two training data labeling approaches were also tested to determine the effectiveness of the model, which is score-based and lexicon-based. The experimental results show that pre-trained models trained in Indonesian have better average accuracy on lexicon-based data. The pre-trained Indonesian model highest accuracy is 84%, with 25 epochs and a training time of 24 minutes. These results are better than all of the machine learning and multilingual pre-trained models.
31. Two-Stage Classifier for COVID-19 Misinformation Detection Using BERT: a Study on Indonesian Tweets
Authors: Douglas Raevan Faisal, Rahmad Mahendra
Categories: cs.CL, cs.SI
Published: 2022-06-30
arXiv: 2206.15359v1
Abstract:
The COVID-19 pandemic has caused globally significant impacts since the beginning of 2020. This brought a lot of confusion to society, especially due to the spread of misinformation through social media. Although there were already several studies related to the detection of misinformation in social media data, most studies focused on the English dataset. Research on COVID-19 misinformation detection in Indonesia is still scarce. Therefore, through this research, we collect and annotate datasets for Indonesian and build prediction models for detecting COVID-19 misinformation by considering the tweet’s relevance. The dataset construction is carried out by a team of annotators who labeled the relevance and misinformation of the tweet data. In this study, we propose the two-stage classifier model using IndoBERT pre-trained language model for the Tweet misinformation detection task. We also experiment with several other baseline models for text classification. The experimental results show that the combination of the BERT sequence classifier for relevance prediction and Bi-LSTM for misinformation detection outperformed other machine learning models with an accuracy of 87.02%. Overall, the BERT utilization contributes to the higher performance of most prediction models. We release a high-quality COVID-19 misinformation Tweet corpus in the Indonesian language, indicated by the high inter-annotator agreement.
32. A Hybrid Classical-Quantum Fine Tuned BERT for Text Classification
Authors: Abu Kaisar Mohammad Masum, Naveed Mahmud, M. Hassan Najafi, Sercan Aygun
Categories: cs.LG, quant-ph
Published: 2025-11-21
arXiv: 2511.17677v1
Abstract:
Fine-tuning BERT for text classification can be computationally challenging and requires careful hyper-parameter tuning. Recent studies have highlighted the potential of quantum algorithms to outperform conventional methods in machine learning and text classification tasks. In this work, we propose a hybrid approach that integrates an n-qubit quantum circuit with a classical BERT model for text classification. We evaluate the performance of the fine-tuned classical-quantum BERT and demonstrate its feasibility as well as its potential in advancing this research area. Our experimental results show that the proposed hybrid model achieves performance that is competitive with, and in some cases better than, the classical baselines on standard benchmark datasets. Furthermore, our approach demonstrates the adaptability of classical-quantum models for fine-tuning pre-trained models across diverse datasets. Overall, the hybrid model highlights the promise of quantum computing in achieving improved performance for text classification tasks.
33. Analysis Acoustic Features for Acoustic Scene Classification and Score fusion of multi-classification systems applied to DCASE 2016 challenge
Authors: Sangwook Park, Seongkyu Mun, Younglo Lee, David K. Han, Hanseok Ko
Categories: cs.SD, eess.AS
Published: 2018-07-13
arXiv: 1807.04970v1
Abstract:
This paper describes an acoustic scene classification method which achieved the 4th ranking result in the IEEE AASP challenge of Detection and Classification of Acoustic Scenes and Events 2016. In order to accomplish the ensuing task, several methods are explored in three aspects: feature extraction, feature transformation, and score fusion for final decision. In the part of feature extraction, several features are investigated for effective acoustic scene classification. For resolving the issue that the same sound can be heard in different places, a feature transformation is applied for better separation for classification. From these, several systems based on different feature sets are devised for classification. The final result is determined by fusing the individual systems. The method is demonstrated and validated by the experiment conducted using the Challenge database.
34. UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction
Authors: Sangmin Lee, Eekgyun Ahn, Woongjib Choi, Hong-Goo Kang
Categories: cs.CL, cs.SD
Published: 2026-06-10
arXiv: 2606.11681v2
Abstract:
We propose UR-BERT, a Romanized transcription-based text-to-speech (TTS) encoder for massively multilingual TTS systems. Conventional grapheme-to-phoneme (G2P)-based approaches are limited to around 100 languages due to the availability of reliable G2P resources. In contrast, UR-BERT scales to 495 languages by unifying diverse writing systems into a shared Romanization representation. To further enhance phonetic fidelity and text-speech alignment, we introduce a speech token prediction objective during training, which encourages the encoder to learn speech-aware phonetic representations in a data-efficient manner. Experiments show that TTS systems built on UR-BERT consistently outperform recent text encoder baselines across a wide range of languages and resource conditions, and demonstrate strong generalization to unseen languages.
35. Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption
Authors: Garam Lee, Minsoo Kim, Jai Hyun Park, Seung-won Hwang, Jung Hee Cheon
Categories: cs.CL
Published: 2022-10-05
arXiv: 2210.02574v1
Abstract:
Embeddings, which compress information in raw text into semantics-preserving low-dimensional vectors, have been widely adopted for their efficacy. However, recent research has shown that embeddings can potentially leak private information about sensitive attributes of the text, and in some cases, can be inverted to recover the original input text. To address these growing privacy challenges, we propose a privatization mechanism for embeddings based on homomorphic encryption, to prevent potential leakage of any piece of information in the process of text classification. In particular, our method performs text classification on the encryption of embeddings from state-of-the-art models like BERT, supported by an efficient GPU implementation of CKKS encryption scheme. We show that our method offers encrypted protection of BERT embeddings, while largely preserving their utility on downstream text classification tasks.
36. BERT-Based Combination of Convolutional and Recurrent Neural Network for Indonesian Sentiment Analysis
Authors: Hendri Murfi, Syamsyuriani, Theresia Gowandi, Gianinna Ardaneswari, Siti Nurrohmah
Categories: cs.CL, cs.LG
Published: 2022-11-10
arXiv: 2211.05273v1
Abstract:
Sentiment analysis is the computational study of opinions and emotions ex-pressed in text. Deep learning is a model that is currently producing state-of-the-art in various application domains, including sentiment analysis. Many researchers are using a hybrid approach that combines different deep learning models and has been shown to improve model performance. In sentiment analysis, input in text data is first converted into a numerical representation. The standard method used to obtain a text representation is the fine-tuned embedding method. However, this method does not pay attention to each word’s context in the sentence. Therefore, the Bidirectional Encoder Representation from Transformer (BERT) model is used to obtain text representations based on the context and position of words in sentences. This research extends the previous hybrid deep learning using BERT representation for Indonesian sentiment analysis. Our simulation shows that the BERT representation improves the accuracies of all hybrid architectures. The BERT-based LSTM-CNN also reaches slightly better accuracies than other BERT-based hybrid architectures.
37. Clinical Trial Information Extraction with BERT
Authors: Xiong Liu, Greg L. Hersch, Iya Khalil, Murthy Devarakonda
Categories: q-bio.QM, cs.CL, cs.LG
Published: 2021-09-11
arXiv: 2110.10027v1
Abstract:
Natural language processing (NLP) of clinical trial documents can be useful in new trial design. Here we identify entity types relevant to clinical trial design and propose a framework called CT-BERT for information extraction from clinical trial text. We trained named entity recognition (NER) models to extract eligibility criteria entities by fine-tuning a set of pre-trained BERT models. We then compared the performance of CT-BERT with recent baseline methods including attention-based BiLSTM and Criteria2Query. The results demonstrate the superiority of CT-BERT in clinical trial NLP.
38. Clickbait Headline Detection in Indonesian News Sites using Multilingual Bidirectional Encoder Representations from Transformers (M-BERT)
Authors: Muhammad N. Fakhruzzaman, Saidah Z. Jannah, Ratih A. Ningrum, Indah Fahmiyah
Categories: cs.CL
Published: 2021-02-02
arXiv: 2102.01497v1
Abstract:
Click counts are related to the amount of money that online advertisers paid to news sites. Such business models forced some news sites to employ a dirty trick of click-baiting, i.e., using a hyperbolic and interesting words, sometimes unfinished sentence in a headline to purposefully tease the readers. Some Indonesian online news sites also joined the party of clickbait, which indirectly degrade other established news sites’ credibility. A neural network with a pre-trained language model M-BERT that acted as a embedding layer is then combined with a 100 nodes hidden layer and topped with a sigmoid classifier was trained to detect clickbait headlines. With a total of 6632 headlines as a training dataset, the classifier performed remarkably well. Evaluated with 5-fold cross validation, it has an accuracy score of 0.914, f1-score of 0.914, precision score of 0.916, and ROC-AUC of 0.92. The usage of multilingual BERT in Indonesian text classification task was tested and is possible to be enhanced further. Future possibilities, societal impact, and limitations of the clickbait detection are discussed.
39. BEiT: BERT Pre-Training of Image Transformers
Authors: Hangbo Bao, Li Dong, Songhao Piao, Furu Wei
Categories: cs.CV, cs.LG
Published: 2021-06-15
arXiv: 2106.08254v2
Abstract:
We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. Following BERT developed in the natural language processing area, we propose a masked image modeling task to pretrain vision Transformers. Specifically, each image has two views in our pre-training, i.e, image patches (such as 16x16 pixels), and visual tokens (i.e., discrete tokens). We first “tokenize” the original image into visual tokens. Then we randomly mask some image patches and fed them into the backbone Transformer. The pre-training objective is to recover the original visual tokens based on the corrupted image patches. After pre-training BEiT, we directly fine-tune the model parameters on downstream tasks by appending task layers upon the pretrained encoder. Experimental results on image classification and semantic segmentation show that our model achieves competitive results with previous pre-training methods. For example, base-size BEiT achieves 83.2% top-1 accuracy on ImageNet-1K, significantly outperforming from-scratch DeiT training (81.8%) with the same setup. Moreover, large-size BEiT obtains 86.3% only using ImageNet-1K, even outperforming ViT-L with supervised pre-training on ImageNet-22K (85.2%). The code and pretrained models are available at https://aka.ms/beit.
40. SkIn: Skimming-Intensive Long-Text Classification Using BERT for Medical Corpus
Authors: Yufeng Zhao, Haiying Che
Categories: cs.CL, cs.AI
Published: 2022-09-13
arXiv: 2209.05741v2
Abstract:
BERT is a widely used pre-trained model in natural language processing. However, since BERT is quadratic to the text length, the BERT model is difficult to be used directly on the long-text corpus. In some fields, the collected text data may be quite long, such as in the health care field. Therefore, to apply the pre-trained language knowledge of BERT to long text, in this paper, imitating the skimming-intensive reading method used by humans when reading a long paragraph, the Skimming-Intensive Model (SkIn) is proposed. It can dynamically select the critical information in the text so that the sentence input into the BERT-Base model is significantly shortened, which can effectively save the cost of the classification algorithm. Experiments show that the SkIn method has achieved superior accuracy than the baselines on long-text classification datasets in the medical field, while its time and space requirements increase linearly with the text length, alleviating the time and space overflow problem of basic BERT on long-text data.
41. Revisiting Few-sample BERT Fine-tuning
Authors: Tianyi Zhang, Felix Wu, Arzoo Katiyar, Kilian Q. Weinberger, Yoav Artzi
Categories: cs.CL, cs.LG
Published: 2020-06-10
arXiv: 2006.05987v3
Abstract:
This paper is a study of fine-tuning of BERT contextual representations, with focus on commonly observed instabilities in few-sample scenarios. We identify several factors that cause this instability: the common use of a non-standard optimization method with biased gradient estimation; the limited applicability of significant parts of the BERT network for down-stream tasks; and the prevalent practice of using a pre-determined, and small number of training iterations. We empirically test the impact of these factors, and identify alternative practices that resolve the commonly observed instability of the process. In light of these observations, we re-visit recently proposed methods to improve few-sample fine-tuning with BERT and re-evaluate their effectiveness. Generally, we observe the impact of these methods diminishes significantly with our modified process.
42. LegalTurk Optimized BERT for Multi-Label Text Classification and NER
Authors: Farnaz Zeidi, Mehmet Fatih Amasyali, Çiğdem Erol
Categories: cs.CL
Published: 2024-06-30
arXiv: 2407.00648v1
Abstract:
The introduction of the Transformer neural network, along with techniques like self-supervised pre-training and transfer learning, has paved the way for advanced models like BERT. Despite BERT’s impressive performance, opportunities for further enhancement exist. To our knowledge, most efforts are focusing on improving BERT’s performance in English and in general domains, with no study specifically addressing the legal Turkish domain. Our study is primarily dedicated to enhancing the BERT model within the legal Turkish domain through modifications in the pre-training phase. In this work, we introduce our innovative modified pre-training approach by combining diverse masking strategies. In the fine-tuning task, we focus on two essential downstream tasks in the legal domain: name entity recognition and multi-label text classification. To evaluate our modified pre-training approach, we fine-tuned all customized models alongside the original BERT models to compare their performance. Our modified approach demonstrated significant improvements in both NER and multi-label text classification tasks compared to the original BERT model. Finally, to showcase the impact of our proposed models, we trained our best models with different corpus sizes and compared them with BERTurk models. The experimental results demonstrate that our innovative approach, despite being pre-trained on a smaller corpus, competes with BERTurk.
43. BertGCN: Transductive Text Classification by Combining GCN and BERT
Authors: Yuxiao Lin, Yuxian Meng, Xiaofei Sun, Qinghong Han, Kun Kuang, Jiwei Li, Fei Wu
Categories: cs.CL
Published: 2021-05-12
arXiv: 2105.05727v4
Abstract:
In this work, we propose BertGCN, a model that combines large scale pretraining and transductive learning for text classification. BertGCN constructs a heterogeneous graph over the dataset and represents documents as nodes using BERT representations. By jointly training the BERT and GCN modules within BertGCN, the proposed model is able to leverage the advantages of both worlds: large-scale pretraining which takes the advantage of the massive amount of raw data and transductive learning which jointly learns representations for both training data and unlabeled test data by propagating label influence through graph convolution. Experiments show that BertGCN achieves SOTA performances on a wide range of text classification datasets. Code is available at https://github.com/ZeroRin/BertGCN.
44. Kaleido-BERT: Vision-Language Pre-training on Fashion Domain
Authors: Mingchen Zhuge, Dehong Gao, Deng-Ping Fan, Linbo Jin, Ben Chen, Haoming Zhou, Minghui Qiu, Ling Shao
Categories: cs.CV
Published: 2021-03-30
arXiv: 2103.16110v3
Abstract:
We present a new vision-language (VL) pre-training model dubbed Kaleido-BERT, which introduces a novel kaleido strategy for fashion cross-modality representations from transformers. In contrast to random masking strategy of recent VL models, we design alignment guided masking to jointly focus more on image-text semantic relations. To this end, we carry out five novel tasks, i.e., rotation, jigsaw, camouflage, grey-to-color, and blank-to-color for self-supervised VL pre-training at patches of different scale. Kaleido-BERT is conceptually simple and easy to extend to the existing BERT framework, it attains new state-of-the-art results by large margins on four downstream tasks, including text retrieval (R@1: 4.03% absolute improvement), image retrieval (R@1: 7.13% abs imv.), category recognition (ACC: 3.28% abs imv.), and fashion captioning (Bleu4: 1.2 abs imv.). We validate the efficiency of Kaleido-BERT on a wide range of e-commerical websites, demonstrating its broader potential in real-world applications.
45. Implications of mappings between ICD clinical diagnosis codes and Human Phenotype Ontology terms
Authors: Amelia LM Tan, Rafael S Gonçalves, William Yuan, Gabriel A Brat, The Consortium for Clinical Characterization of COVID-19 by EHR, Robert Gentleman, Isaac S Kohane
Categories: cs.DB
Published: 2024-07-11
arXiv: 2407.08874v1
Abstract:
Objective: Integrating EHR data with other resources is essential in rare disease research due to low disease prevalence. Such integration is dependent on the alignment of ontologies used for data annotation. The International Classification of Diseases (ICD) is used to annotate clinical diagnoses; the Human Phenotype Ontology (HPO) to annotate phenotypes. Although these ontologies overlap in biomedical entities described, the extent to which they are interoperable is unknown. We investigate how well aligned these ontologies are and whether such alignments facilitate EHR data integration. Materials and Methods: We conducted an empirical analysis of the coverage of mappings between ICD and HPO. We interpret this mapping coverage as a proxy for how easily clinical data can be integrated with research ontologies such as HPO. We quantify how exhaustively ICD codes are mapped to HPO by analyzing mappings in the UMLS Metathesaurus. We analyze the proportion of ICD codes mapped to HPO within a real-world EHR dataset. Results and Discussion: Our analysis revealed that only 2.2% of ICD codes have direct mappings to HPO in UMLS. Within our EHR dataset, less than 50% of ICD codes have mappings to HPO terms. ICD codes that are used frequently in EHR data tend to have mappings to HPO; ICD codes that represent rarer medical conditions are seldom mapped. Conclusion: We find that interoperability between ICD and HPO via UMLS is limited. While other mapping sources could be incorporated, there are no established conventions for what resources should be used to complement UMLS.
46. LV-BERT: Exploiting Layer Variety for BERT
Authors: Weihao Yu, Zihang Jiang, Fei Chen, Qibin Hou, Jiashi Feng
Categories: cs.CL, cs.AI, cs.LG
Published: 2021-06-22
arXiv: 2106.11740v2
Abstract:
Modern pre-trained language models are mostly built upon backbones stacking self-attention and feed-forward layers in an interleaved order. In this paper, beyond this stereotyped layer pattern, we aim to improve pre-trained models by exploiting layer variety from two aspects: the layer type set and the layer order. Specifically, besides the original self-attention and feed-forward layers, we introduce convolution into the layer type set, which is experimentally found beneficial to pre-trained models. Furthermore, beyond the original interleaved order, we explore more layer orders to discover more powerful architectures. However, the introduced layer variety leads to a large architecture space of more than billions of candidates, while training a single candidate model from scratch already requires huge computation cost, making it not affordable to search such a space by directly training large amounts of candidate models. To solve this problem, we first pre-train a supernet from which the weights of all candidate models can be inherited, and then adopt an evolutionary algorithm guided by pre-training accuracy to find the optimal architecture. Extensive experiments show that LV-BERT model obtained by our method outperforms BERT and its variants on various downstream tasks. For example, LV-BERT-small achieves 79.8 on the GLUE testing set, 1.8 higher than the strong baseline ELECTRA-small.
47. IndoSum: A New Benchmark Dataset for Indonesian Text Summarization
Authors: Kemal Kurniawan, Samuel Louvan
Categories: cs.CL
Published: 2018-10-12
arXiv: 1810.05334v5
Abstract:
Automatic text summarization is generally considered as a challenging task in the NLP community. One of the challenges is the publicly available and large dataset that is relatively rare and difficult to construct. The problem is even worse for low-resource languages such as Indonesian. In this paper, we present IndoSum, a new benchmark dataset for Indonesian text summarization. The dataset consists of news articles and manually constructed summaries. Notably, the dataset is almost 200x larger than the previous Indonesian summarization dataset of the same domain. We evaluated various extractive summarization approaches and obtained encouraging results which demonstrate the usefulness of the dataset and provide baselines for future research. The code and the dataset are available online under permissive licenses.
48. FinAI-BERT: A Transformer-Based Model for Sentence-Level Detection of AI Disclosures in Financial Reports
Authors: Muhammad Bilal Zafar
Categories: q-fin.CP, cs.CL, econ.GN, q-fin.GN
Published: 2025-06-29
arXiv: 2507.01991v1
Abstract:
The proliferation of artificial intelligence (AI) in financial services has prompted growing demand for tools that can systematically detect AI-related disclosures in corporate filings. While prior approaches often rely on keyword expansion or document-level classification, they fall short in granularity, interpretability, and robustness. This study introduces FinAI-BERT, a domain-adapted transformer-based language model designed to classify AI-related content at the sentence level within financial texts. The model was fine-tuned on a manually curated and balanced dataset of 1,586 sentences drawn from 669 annual reports of U.S. banks (2015 to 2023). FinAI-BERT achieved near-perfect classification performance (accuracy of 99.37 percent, F1 score of 0.993), outperforming traditional baselines such as Logistic Regression, Naive Bayes, Random Forest, and XGBoost. Interpretability was ensured through SHAP-based token attribution, while bias analysis and robustness checks confirmed the model’s stability across sentence lengths, adversarial inputs, and temporal samples. Theoretically, the study advances financial NLP by operationalizing fine-grained, theme-specific classification using transformer architectures. Practically, it offers a scalable, transparent solution for analysts, regulators, and scholars seeking to monitor the diffusion and framing of AI across financial institutions.
49. Multi-class Text Classification using BERT-based Active Learning
Authors: Sumanth Prabhu, Moosa Mohamed, Hemant Misra
Categories: cs.IR, cs.LG
Published: 2021-04-27
arXiv: 2104.14289v2
Abstract:
Text Classification finds interesting applications in the pickup and delivery services industry where customers require one or more items to be picked up from a location and delivered to a certain destination. Classifying these customer transactions into multiple categories helps understand the market needs for different customer segments. Each transaction is accompanied by a text description provided by the customer to describe the products being picked up and delivered which can be used to classify the transaction. BERT-based models have proven to perform well in Natural Language Understanding. However, the product descriptions provided by the customers tend to be short, incoherent and code-mixed (Hindi-English) text which demands fine-tuning of such models with manually labelled data to achieve high accuracy. Collecting this labelled data can prove to be expensive. In this paper, we explore Active Learning strategies to label transaction descriptions cost effectively while using BERT to train a transaction classification model. On TREC-6, AG’s News Corpus and an internal dataset, we benchmark the performance of BERT across different Active Learning strategies in Multi-Class Text Classification.
50. KliniskVestBERT: BERT Model Specialised to Norwegian Clinical Texts
Authors: Christian Autenried, Cosimo Persia
Categories: cs.CL, cs.AI
Published: 2026-06-01
arXiv: 2606.01904v2
Abstract:
The increasing application of Natural Language Processing (NLP) in healthcare demands language models specifically attuned to the complexities of clinical language. This work introduces KliniskVestBERT, a suite of three BERT-based encoder models pre-trained on a substantial corpus of real-world, de-identified Norwegian clinical texts from Helse Vest. We continue pretraining existing language models Nb-BERT-large, NorBERT3-large, and ModernBERT on our specialized clinical dataset. This dataset is based on a representative population of Helse Vest patients. The included document types are carefully curated to encompass a broad clinical spectrum in bokmål and nynorsk including discharge summaries, surgical reports, nursing notes etc. ensuring comprehensive representation of the linguistic landscape within Norwegian healthcare settings. Evaluation on three synthtetic Norwegian clinical benchmark datasets and two real-world problems demonstrates that each of our clinically specialized models consistently outperforms their baseline counterparts, highlighting the significant benefit of domain-specific pre-training for NLP tasks within the clinical domain. The project was a joint effort by all Helse Vest entities (Helse Bergen, Helse Fonna, Helse Førde and Helse Stavanger) with DIPS under the project lead of Helse Vest ICT.