Pre-trained language models with domain knowledge for biomedical extractive summarization

In this investigation, we propose a solution for the author’s gender identification task called AGI-P. This task has several real-world applications across different fields, such as marketing and advertising, forensic linguistics, sociology, recommendation systems, language processing, historical analysis, education, and language learning. We created a new dataset to evaluate our proposed method. The dataset is balanced in terms of gender using a random sampling method and consists of 1944 samples in total. We use accuracy as an evaluation measure and compare the performance of the proposed solution (AGI-P) against state-of-the-art machine learning classifiers and fine-tuned pre-trained multilingual language models such as DistilBERT, mBERT, XLM-RoBERTa, and Multilingual DEBERTa. In this regard, we also propose a customized fine-tuning strategy that improves the accuracy of the pre-trained language models for the author gender identification task. Our extensive experimental studies reveal that our solution (AGI-P) outperforms the well-known machine learning classifiers and fine-tuned pre-trained multilingual language models with an accuracy level of 92.03%. Moreover, the pre-trained multilingual language models, fine-tuned with the proposed customized strategy, outperform the fine-tuned pre-trained language models using an out-of-the-box fine-tuning strategy. The codebase and the corpus will be publicly available for scholars in this area upon publication.

Korean is the native and official language spoken by Chinese-Korean people, and Weibo is a social media software with a huge number of users in China. Currently, there is few studies related to sentiment analysis of Korean-language Weibo texts posted by Chinese-Korean users. In this paper, we propose a sentiment classification method for Chinese-Korean Weibo based on pre-trained language model and transfer learning. Firstly, we crawled the Chinese-Korean Weibo data from Sina Weibo and label them with sentiment to get the Chinese-Korean Weibo sentiment analysis (CKWSA) dataset. Secondly, to solve the problem of few training samples of the Chinese-Korean Weibo sentiment analysis dataset, we fine-tune the classifier based on the pre-trained Korean language model on the Korean Twitter sentiment analysis dataset to obtain the Korean Twitter sentiment classification model; and further fine-tune the model on CKWSA dataset to get Chinese-Korean Weibo sentiment classification model. The experiments show that the proposed classification method based on pre-trained language model and transfer learning has great performance, and there is an improvement compared other baselines on the Chinese-Korean Weibo sentiment analysis dataset.

The increasingly large amount of available biomedical literature is making it difficult to gather and synthesise all the necessary information. Moreover, this domain-specific task demands a high level of reliability in the generated text and concepts. Pre-trained large language models have recently shown promising results. Given the specific requirements of biomedical text summarisation, our evaluation focuses on extractive models, prioritising the accuracy of the generated text. In this article, we evaluate the capabilities of 18 general-domain and biomedical pre-trained language models in various configurations on the biomedical extractive summarisation task using one single and two multi-document datasets consisting of 33,000, 5,000 and 470,000 PubMed articles, respectively. We performed the comparison using several well-known metrics, namely ROUGE-1, ROUGE-2, ROUGE-L, BERTScore, BLEU and METEOR. The main contribution of this work lies in providing a detailed performance analysis, highlighting the differences between general-domain and biomedical models, and identifying key factors that influence model performance in extractive summarisation tasks within the biomedical domain. Experimental results show that biomedical models tend to result in higher recall, while general-domain models produce higher precision, while general-domain models produce higher precision. This corresponds to more expressive summaries for biomedical models and shorter summaries for general-domain models.

This paper presents a novel model for extractive summarization that integrates context representation from a pre-trained language model (PLM), such as BERT, with prior knowledge derived from unsupervised learning methods. Sentence importance assessment is crucial in extractive summarization, with prior knowledge providing indicators of sentence importance within a document. Our model introduces a method for estimating sentence importance based on prior knowledge, complementing the contextual representation offered by PLMs like BERT. Unlike previous approaches that primarily relied on PLMs alone, our model leverages both contextual representation and prior knowledge extracted from each input document. By conditioning the model on prior knowledge, it emphasizes key sentences in generating the final summary. We evaluate our model on three benchmark datasets across two languages, demonstrating improved performance compared to strong baseline methods in extractive summarization. Additionally, our ablation study reveals that injecting knowledge into certain first attention layers yields greater benefits than others. The model code is publicly available for further exploration.

This paper describes the models designated for the MEDIQA 2019 shared tasks by the team PANLP. We take advantages of the recent advances in pre-trained bidirectional transformer language models such as BERT (Devlin et al., 2018) and MT-DNN (Liu et al., 2019b). We find that pre-trained language models can significantly outperform traditional deep learning models. Transfer learning from the NLI task to the RQE task is also experimented, which proves to be useful in improving the results of fine-tuning MT-DNN large. A knowledge distillation process is implemented, to distill the knowledge contained in a set of models and transfer it into an single model, whose performance turns out to be comparable with that obtained by the ensemble of that set of models. Finally, for test submissions, model ensemble and a re-ranking process are implemented to boost the performances. Our models participated in all three tasks and ranked the 1st place for the RQE task, and the 2nd place for the NLI task, and also the 2nd place for the QA task.

Since the development and wide use of pretrained language models (PLMs), several approaches have been applied to boost their performance on downstream tasks in specific domains, such as biomedical or scientific domains. Additional pre-training with in-domain texts is the most common approach for providing domain-specific knowledge to PLMs. However, these pre-training methods require considerable in-domain data and training resources and a longer training time. Moreover, the training must be re-performed whenever a new PLM emerges. In this study, we propose a domain knowledge transferring (DoKTra) framework for PLMs without additional in-domain pretraining. Specifically, we extract the domain knowledge from an existing in-domain pretrained language model and transfer it to other PLMs by applying knowledge distillation. In particular, we employ activation boundary distillation, which focuses on the activation of hidden neurons. We also apply an entropy regularization term in both teacher training and distillation to encourage the model to generate reliable output probabilities, and thus aid the distillation. By applying the proposed DoKTra framework to downstream tasks in the biomedical, clinical, and financial domains, our student models can retain a high percentage of teacher performance and even outperform the teachers in certain tasks. Our code is available at https://github.com/DMCB-GIST/DoKTra.

PurposeSafety management plays an important part in coal mine construction. Due to complex data, the implementation of the construction safety knowledge scattered in standards poses a challenge. This paper aims to develop a knowledge extraction model to automatically and efficiently extract domain knowledge from unstructured texts.Design/methodology/approachBidirectional encoder representations from transformers (BERT)-bidirectional long short-term memory (BiLSTM)-conditional random field (CRF) method based on a pre-training language model was applied to carry out knowledge entity recognition in the field of coal mine construction safety in this paper. Firstly, 80 safety standards for coal mine construction were collected, sorted out and marked as a descriptive corpus. Then, the BERT pre-training language model was used to obtain dynamic word vectors. Finally, the BiLSTM-CRF model concluded the entity’s optimal tag sequence.FindingsAccordingly, 11,933 entities and 2,051 relationships in the standard specifications texts of this paper were identified and a language model suitable for coal mine construction safety management was proposed. The experiments showed that F1 values were all above 60% in nine types of entities such as security management. F1 value of this model was more than 60% for entity extraction. The model identified and extracted entities more accurately than conventional methods.Originality/valueThis work completed the domain knowledge query and built a Q&A platform via entities and relationships identified by the standard specifications suitable for coal mines. This paper proposed a systematic framework for texts in coal mine construction safety to improve efficiency and accuracy of domain-specific entity extraction. In addition, the pretraining language model was also introduced into the coal mine construction safety to realize dynamic entity recognition, which provides technical support and theoretical reference for the optimization of safety management platforms.

JointMatcher: Numerically-aware entity matching using pre-trained language models with attention concentration

A rapidly rising number of open judgment documents has increased the requirement for automatic summarization. Since Chinese judgment documents are characterized by a lengthy and logical structure, extractive summarization is an effective method for them. However, existing extractive models generally cannot capture information between sentences. In order to enable the model to obtain long-term information in the judgment documents, this paper proposes an extractive model using sentence embeddings and a two-layers memory network. A pre-trained language model is used to encode sentences in judgment documents. Then the whitening operation is applied to get isotropic sentence embeddings, which makes the subsequent classification more accurate. These embeddings are fed into a unidirectional memory network to fuse previous sentence embeddings. A bidirectional memory network is followed to introduce position information of sentences. The experimental results show that our proposed model outperforms the baseline methods on the SFZY dataset from CAIL2020.

Biomedical text summarization helps biomedical information seekers avoid information overload by reducing the length of a document while preserving the contents' essence. Our systematic review investigates the most recent biomedical text summarization researches on biomedical literature and electronic health records by analyzing their techniques, areas of application, and evaluation methods. We identify gaps and propose potential directions for future research. This review followed the PRISMA methodology and replicated the approaches adopted by the previous systematic review published on the same topic. We searched 4 databases (PubMed, ACM Digital Library, Scopus, and Web of Science) from January 1, 2013 to April 8, 2021. Two reviewers independently screened title, abstract, and full-text for all retrieved articles. The conflicts were resolved by the third reviewer. The data extraction of the included articles was in 5 dimensions: input, purpose, output, method, and evaluation. Fifty-eight out of 7235 retrieved articles met the inclusion criteria. Thirty-nine systems used single-document biomedical research literature as their input, 17 systems were explicitly designed for clinical support, 47 systems generated extractive summaries, and 53 systems adopted hybrid methods combining computational linguistics, machine learning, and statistical approaches. As for the assessment, 51 studies conducted an intrinsic evaluation using predefined metrics. This study found that current biomedical text summarization systems have achieved good performance using hybrid methods. Studies on electronic health records summarization have been increasing compared to a previous survey. However, the majority of the works still focus on summarizing literature.

With the success of down streaming task using English pre-trained language model, the pre-trained Chinese language model is also necessary to get better performance of Chinese NLP tasks. Unlike the English language, Chinese has its special characters such as glyph information. So in this article, we propose the Chinese pre-trained language model named StyleBERT which incorporate the following embedding information to enhance the savvy of language model, such as word, pinyin, five stroke and chaizi. The experiments show that the model achieves well performances on a wide range of Chinese NLP tasks.

Sentence Boundary Disambiguation (SBD) is crucial for building datasets for tasks such as machine translation, syntactic analysis, and semantic analysis. Currently, most automatic sentence segmentation in Tibetan adopts the methods of rule-based and statistical learning, as well as the combination of the two, which have high requirements on the corpus and the linguistic foundation of the researchers and are more costly to annotate manually. In this study, we explore Tibetan SBD using deep learning technology. Initially, we analyze Tibetan characteristics and various subword techniques, selecting Byte Pair Encoding (BPE) and Sentencepiece (SP) for text segmentation and training the Bidirectional Encoder Representations from Transformers (BERT) pre-trained language model. Secondly, we studied the Tibetan SBD based on different BERT pre-trained language models, which mainly learns the ambiguity of the shad (“།”) in different positions in modern Tibetan texts and determines through the model whether the shad (“།”) in the texts has the function of segmenting sentences. Meanwhile, this study introduces four models, BERT-CNN, BERT-RNN, BERT-RCNN, and BERT-DPCNN, based on the BERT model for performance comparison. Finally, to verify the performance of the pre-trained language models on the SBD task, this study conducts SBD experiments on both the publicly available Tibetan pre-trained language model TiBERT and the multilingual pre-trained language model (Multi-BERT). The experimental results show that the F1 score of the BERT (BPE) model trained in this study reaches 95.32% on 465,669 Tibetan sentences, nearly five percentage points higher than BERT (SP) and Multi-BERT. The SBD method based on pre-trained language models in this study lays the foundation for establishing datasets for the later tasks of Tibetan pre-training, summary extraction, and machine translation.

Homonymy can easily raise lexical ambiguity due to the misunderstanding of its multiple senses.Correct recognition of homonym sense greatly relies on its surrounding context.This ambiguous nature makes homonyms an appropriate testbed for examining the contextualization capability of pre-trained (PLM) and large language models (LLMs).Considering the impact of part of speech (POS) on homonym disambiguation and the prevalence of English-focused studies in word embedding research, this study extends to Chinese and provides a comprehensive layer-wise analysis of homonym representations in both languages, spanning same and different POS categories, across four families of PLMs/LLMs (BERT, GPT-2, Llama 3, Qwen 2.5).Through the creation of a synthetic dataset and computation of disambiguation score (D-Score), we found that: (1) no universal layer depth excels in differentiating homonym representations; (2) bidirectional models produce better contextualized homonym representations compared to much larger autoregressive models; (3) most importantly, POS affects homonym representations in models in ways that differ from human research findings.The individual differences between LLMs uncovered in our study challenge the simplistic understanding of their inner workings.This reveals a compelling research frontier: conducting controlled experiments with purposefully manipulated inputs to enhance the interpretability of LLMs.We have made our dataset and codes available publicly at https://github.com/neurothew/ exploring-homonym-rep-in-llm.

Antimicrobial peptides (AMPs) are vital components of innate immunotherapy. Existing approaches mainly rely on either deep learning for the automatic extraction of sequence features or traditional manual amino acid features combined with machine learning. The peptide sequence contains symmetrical sequence motifs or repetitive amino acid patterns, which may be related to the function and structure of the peptide. Recently, the advent of large language models has significantly boosted the representational power of sequence pattern features. In light of this, we present a novel AMP predictor called UniproLcad, which integrates three prominent protein language models—ESM-2, ProtBert, and UniRep—to obtain a more comprehensive representation of protein features. UniproLcad utilizes deep learning networks, encompassing the bidirectional long and short memory network (Bi-LSTM) and one-dimensional convolutional neural networks (1D-CNN), while also integrating an attention mechanism to enhance its capabilities. These deep learning frameworks, coupled with pre-trained language models, efficiently extract multi-view features from antimicrobial peptide sequences and assign attention weights to them. Through ten-fold cross-validation and independent testing, UniproLcad demonstrates competitive performance in the field of antimicrobial peptide identification. This integration of diverse language models and deep learning architectures enhances the accuracy and reliability of predicting antimicrobial peptides, contributing to the advancement of computational methods in this field.

Depression is a serious mental health disorder that poses a major public health concern in Thailand and have a profound impact on individuals' physical and mental health. In addition, the lack of number to mental health services and limited number of psychiatrists in Thailand make depression particularly challenging to diagnose and treat, leaving many individuals with the condition untreated. Recent studies have explored the use of natural language processing to enable access to the classification of depression, particularly with a trend toward transfer learning from pre-trained language model. In this study, we attempted to evaluate the effectiveness of using XLM-RoBERTa, a pre-trained multi-lingual language model supporting the Thai language, for the classification of depression from a limited set of text transcripts from speech responses. Twelve Thai depression assessment questions were developed to collect text transcripts of speech responses to be used with XLM-RoBERTa in transfer learning. The results of transfer learning with text transcription from speech responses of 80 participants (40 with depression and 40 normal control) showed that when only one question (Q1) of "How are you these days?" was used, the recall, precision, specificity, and accuracy were 82.5%, 84.65, 85.00, and 83.75%, respectively. When utilizing the first three questions from Thai depression assessment tasks (Q1 - Q3), the values increased to 87.50%, 92.11%, 92.50%, and 90.00%, respectively. The local interpretable model explanations were analyzed to determine which words contributed the most to the model's word cloud visualization. Our findings were consistent with previously published literature and provide similar explanation for clinical settings. It was discovered that the classification model for individuals with depression relied heavily on negative terms such as 'not,' 'sad,', 'mood', 'suicide', 'bad', and 'bore' whereas normal control participants used neutral to positive terms such as 'recently,' 'fine,', 'normally', 'work', and 'working'. The findings of the study suggest that screening for depression can be facilitated by eliciting just three questions from patients with depression, making the process more accessible and less time-consuming while reducing the already huge burden on healthcare workers.