Pretraining large neural language models, such as BERT, has led to impressive gains on many natural language processing (NLP) tasks. However, most pretraining efforts focus on general domain corpora, such as newswire and Web. A prevailing assumption is that even domain-specific pretraining can benefit by starting from general-domain language models. In this paper, we challenge this assumption by showing that for domains with abundant unlabeled text, such as biomedicine, pretraining language models from scratch results in substantial gains over continual pretraining of general-domain language models. To facilitate this investigation, we compile a comprehensive biomedical NLP benchmark from publicly-available datasets. Our experiments show that domain-specific pretraining serves as a solid foundation for a wide range of biomedical NLP tasks, leading to new state-of-the-art results across the board. Further, in conducting a thorough evaluation of modeling choices, both for pretraining and task-specific fine-tuning, we discover that some common practices are unnecessary with BERT models, such as using complex tagging schemes in named entity recognition (NER). To help accelerate research in biomedical NLP, we have released our state-of-the-art pretrained and task-specific models for the community, and created a leaderboard featuring our BLURB benchmark (short for Biomedical Language Understanding & Reasoning Benchmark) at https://aka.ms/BLURB.
Text Mining Unit Barcelona Supercomputing Center（文本挖掘组 巴塞罗那超级计算中心）
This work presents biomedical and clinical language models for Spanish by experimenting with different pretraining choices, such as masking at word and subword level, varying the vocabulary size and testing with domain data, looking for better language representations. Interestingly, in the absence of enough clinical data to train a model from scratch, we applied mixed-domain pretraining and cross-domain transfer approaches to generate a performant bio-clinical model suitable for real-world clinical data. We evaluated our models on Named Entity Recognition (NER) tasks for biomedical documents …
Deep neural language models have set new breakthroughs in many tasks of Natural Language Processing (NLP). Recent work has shown that deep transformer language models (pretrained on large amounts of texts) can achieve high levels of task-specific few-shot performance comparable to state-of-the-art models. However, the ability of these large language models in few-shot transfer learning has not yet been explored in the biomedical domain. We investigated the performance of two powerful transformer language models, i.e. GPT-3 and BioBERT, in few-shot settings on various biomedical NLP tasks. The …
Hierarchical Pretraining for Biomedical Term Embeddings
Stanford University（斯坦福大学）；Tsinghua University（清华大学）；Beijing Institute of Technology（北京理工大学）；Alibaba Damo Academy（阿里巴巴达摩院）；Harvard T.H. Chan School of Public Health（哈佛陈曾熙公共卫生学院）
National Institute of Technology Trichy（蒂鲁吉拉伯利国立理工学院）
Transformer-based pretrained language models (PLMs) have started a new era in modern natural language processing (NLP). These models combine the power of transformers, transfer learning, and self-supervised learning (SSL). Following the success of these models in the general domain, the biomedical research community has developed various in-domain PLMs starting from BioBERT to the latest BioELECTRA and BioALBERT models. We strongly believe there is a need for a survey paper that can provide a comprehensive survey of various transformer-based biomedical pretrained language models (BPLMs). In th…
Stony Brook University（石溪大学）；Delft University of Technology（代尔夫特理工大学）；University of Arizona（亚利桑那大学）
Can language models read biomedical texts and explain the biomedical mechanisms discussed? In this work we introduce a biomedical mechanism summarization task. Biomedical studies often investigate the mechanisms behind how one entity (e.g., a protein or a chemical) affects another in a biological context. The abstracts of these publications often include a focused set of sentences that present relevant supporting statements regarding such relationships, associated experimental evidence, and a concluding sentence that summarizes the mechanism underlying the relationship. We leverage this struct…
Term clustering is important in biomedical knowledge graph construction. Using similarities between terms embedding is helpful for term clustering. State-of-the-art term embeddings leverage pretrained language models to encode terms, and use synonyms and relation knowledge from knowledge graphs to guide contrastive learning. These embeddings provide close embeddings for terms belonging to the same concept. However, from our probing experiments, these embeddings are not sensitive to minor textual differences which leads to failure for biomedical term clustering. To alleviate this problem, we ad…
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）
Foundation models trained on large-scale dataset gain a recent surge in CV and NLP. In contrast, development in biomedical domain lags far behind due to data scarcity. To address this issue, we build and release PMC-OA, a biomedical dataset with 1.6M image-caption pairs collected from PubMedCentral's OpenAccess subset, which is 8 times larger than before. PMC-OA covers diverse modalities or diseases, with majority of the image-caption samples aligned at finer-grained level, i.e., subfigure and subcaption. While pretraining a CLIP-style model on PMC-OA, our model named PMC-CLIP achieves state-o…
Benchmarking large language models for biomedical natural language processing applications and recommendations
Yale University（耶鲁大学）；National Institutes of Health（美国国立卫生研究院）；University of Texas Health Science at Houston（休斯顿德克萨斯大学健康科学中心）；University of Minnesota（明尼苏达大学）
Pretraining a language model (LM) on text has been shown to help various downstream NLP tasks. Recent works show that a knowledge graph (KG) can complement text data, offering structured background knowledge that provides a useful scaffold for reasoning. However, these works are not pretrained to learn a deep fusion of the two modalities at scale, limiting the potential to acquire fully joint representations of text and KG. Here we propose DRAGON (Deep Bidirectional Language-Knowledge Graph Pretraining), a self-supervised approach to pretraining a deeply joint language-knowledge foundation mod…
Isfahan University of Technology（伊斯法罕理工大学）；Isfahan University of Medical Sciences（伊斯法罕医科大学）
Word embeddings have found their way into a wide range of natural language processing tasks including those in the biomedical domain. While these vector representations successfully capture semantic and syntactic word relations, hidden patterns and trends in the data, they fail to offer interpretability. Interpretability is a key means to justification which is an integral part when it comes to biomedical applications. We present an inclusive study on interpretability of word embeddings in the medical domain, focusing on the role of sparse methods. Qualitative and quantitative measurements and…
Humboldt-Universität zu Berlin（柏林洪堡大学）；EleutherAI；Stanford University（斯坦福大学）；BigScience；Max Delbrück Center for Molecular Medicine（马克斯·德尔布吕克分子医学中心）；Sherlock Biosciences（夏洛克生物科学公司）；Tempus Labs Inc.（Tempus实验室公司）；University of Virginia（弗吉尼亚大学）；Immuneering（Immuneering公司）；Booz Allen Hamilton（博思艾伦咨询公司）；Medical University of Vienna（维也纳医科大学）；Brown University（布朗大学）；TU Wien（维也纳工业大学）；The Hong Kong University of Science and Technology（香港科技大学）
Training and evaluating language models increasingly requires the construction of meta-datasets --diverse collections of curated data with clear provenance. Natural language prompting has recently lead to improved zero-shot generalization by transforming existing, supervised datasets into a diversity of novel pretraining tasks, highlighting the benefits of meta-dataset curation. While successful in general-domain text, translating these data-centric approaches to biomedical language modeling remains challenging, as labeled biomedical datasets are significantly underrepresented in popular data …
University of Cambridge（剑桥大学）；Monash University（莫纳什大学）；Amazon Alexa（亚马逊Alexa）
Despite the widespread success of self-supervised learning via masked language models (MLM), accurately capturing fine-grained semantic relationships in the biomedical domain remains a challenge. This is of paramount importance for entity-level tasks such as entity linking where the ability to model entity relations (especially synonymy) is pivotal. To address this challenge, we propose SapBERT, a pretraining scheme that self-aligns the representation space of biomedical entities. We design a scalable metric learning framework that can leverage UMLS, a massive collection of biomedical ontologi…
A Natural Language Processing Approach to Support Biomedical Data Harmonization: Leveraging Large Language Models
Boston University Chobanian & Avedisian School of Medicine（波士顿大学乔巴尼安与阿维迪西安医学院）；Boston University Faculty of Computing & Data Sciences（波士顿大学计算与数据科学学院）；Slone Epidemiology Center（斯隆流行病学中心）；Boston University School of Public Health（波士顿大学公共卫生学院）
Tsinghua University（清华大学）；International Digital Economy Academy（国际数字经济研究院）
Pretrained language models have served as important backbones for natural language processing. Recently, in-domain pretraining has been shown to benefit various domain-specific downstream tasks. In the biomedical domain, natural language generation (NLG) tasks are of critical importance, while understudied. Approaching natural language understanding (NLU) tasks as NLG achieves satisfying performance in the general domain through constrained language generation or language prompting. We emphasize the lack of in-domain generative language models and the unsystematic generative downstream benchma…
The recent success of question answering systems is largely attributed to pre-trained language models. However, as language models are mostly pre-trained on general domain corpora such as Wikipedia, they often have difficulty in understanding biomedical questions. In this paper, we investigate the performance of BioBERT, a pre-trained biomedical language model, in answering biomedical questions including factoid, list, and yes/no type questions. BioBERT uses almost the same structure across various question types and achieved the best performance in the 7th BioASQ Challenge (Task 7b, Phase B).…
Motivation: A perennial challenge for biomedical researchers and clinical practitioners is to stay abreast with the rapid growth of publications and medical notes. Natural language processing (NLP) has emerged as a promising direction for taming information overload. In particular, large neural language models facilitate transfer learning by pretraining on unlabeled text, as exemplified by the successes of BERT models in various NLP applications. However, fine-tuning such models for an end task remains challenging, especially with small labeled datasets, which are common in biomedical NLP. Res…
Pre-trained Language Models in Biomedical Domain: A Systematic Survey
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；SRIBD（深圳市大数据研究院）；University of Manchester（曼彻斯特大学）；University of Amsterdam（阿姆斯特丹大学）；Halmstad University（哈尔姆斯塔德大学）；The University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心）；Mila（米拉人工智能研究所）；University of Montreal（蒙特利尔大学）
Korea University（高丽大学）；Princeton University（普林斯顿大学）；Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院）；NAVER AI Lab（NAVER AI实验室）
Pre-trained language models (LMs) have become ubiquitous in solving various natural language processing (NLP) tasks. There has been increasing interest in what knowledge these LMs contain and how we can extract that knowledge, treating LMs as knowledge bases (KBs). While there has been much work on probing LMs in the general domain, there has been little attention to whether these powerful LMs can be used as domain-specific KBs. To this end, we create the BioLAMA benchmark, which is comprised of 49K biomedical factual knowledge triples for probing biomedical LMs. We find that biomedical LMs wi…
School of Computer Science, University of Sydney（悉尼大学计算机科学学院）；School of Information Technology, Deakin University（迪肯大学信息技术学院）
In recent years, with the growing amount of biomedical documents, coupled with advancement in natural language processing algorithms, the research on biomedical named entity recognition (BioNER) has increased exponentially. However, BioNER research is challenging as NER in the biomedical domain are: (i) often restricted due to limited amount of training data, (ii) an entity can refer to multiple types and concepts depending on its context and, (iii) heavy reliance on acronyms that are sub-domain specific. Existing BioNER approaches often neglect these issues and directly adopt the state-of-the…
Using Pretrained Large Language Model with Prompt Engineering to Answer Biomedical Questions
Georgia Institute of Technology（佐治亚理工学院）；Peoples' Friendship University of Russia (RUDN University)（俄罗斯人民友谊大学（RUDN大学））；Joint Institute for Nuclear Research（联合核研究所）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；University of Skövde（舍夫德大学）
BioInstruct: Instruction Tuning of Large Language Models for Biomedical Natural Language Processing
Manning College of Information and Computer Sciences, University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校曼宁信息与计算机科学学院）；University of Massachusetts Medical School（马萨诸塞大学医学院）；Miner School of Computer and Information Sciences, University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校迈纳计算机与信息科学学院）；VA Bedford Health Care（贝德福德退伍军人保健中心）
Information overload is a prevalent challenge in many high-value domains. A prominent case in point is the explosion of the biomedical literature on COVID-19, which swelled to hundreds of thousands of papers in a matter of months. In general, biomedical literature expands by two papers every minute, totalling over a million new papers every year. Search in the biomedical realm, and many other vertical domains is challenging due to the scarcity of direct supervision from click logs. Self-supervised learning has emerged as a promising direction to overcome the annotation bottleneck. We propose a…
National Institute of Technology Trichy（特里奇国立理工学院）
Transformer-based pretrained language models (T-PTLMs) have achieved great success in almost every NLP task. The evolution of these models started with GPT and BERT. These models are built on the top of transformers, self-supervised learning and transfer learning. Transformed-based PTLMs learn universal language representations from large volumes of text data using self-supervised learning and transfer this knowledge to downstream tasks. These models provide good background knowledge to downstream tasks which avoids training of downstream models from scratch. In this comprehensive survey paper…
Manipal Institute of Technology（马尼帕尔理工学院）；Elsevier Labs（爱思唯尔实验室）
Biomedical Named Entity Recognition (NER) is a challenging problem in biomedical information processing due to the widespread ambiguity of out of context terms and extensive lexical variations. Performance on bioNER benchmarks continues to improve due to advances like BERT, GPT, and XLNet. FLAIR (1) is an alternative embedding model which is less computationally intensive than the others mentioned. We test FLAIR and its pretrained PubMed embeddings (which we term BioFLAIR) on a variety of bio NER tasks and compare those with results from BERT-type networks. We also investigate the effects of a…
Language model (LM) pretraining can learn various knowledge from text corpora, helping downstream tasks. However, existing methods such as BERT model a single document, and do not capture dependencies or knowledge that span across documents. In this work, we propose LinkBERT, an LM pretraining method that leverages links between documents, e.g., hyperlinks. Given a text corpus, we view it as a graph of documents and create LM inputs by placing linked documents in the same context. We then pretrain the LM with two joint self-supervised objectives: masked language modeling and our new proposal, …
Beyond Captions: Context-Grounded Reconstruction for Biomedical Multimodal Continued Pretraining
The Hong Kong Polytechnic University（香港理工大学）；Sun Yat-sen University（中山大学）；InfiX.ai；PolyU-Daya Bay Technology and Innovation Research Institute（PolyU-大亚湾技术与创新研究院）
University of Copenhagen（哥本哈根大学）；PricewaterhouseCoopers (PwC)（普华永道）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）
Domain adaptive pretraining, i.e. the continued unsupervised pretraining of a language model on domain-specific text, improves the modelling of text for downstream tasks within the domain. Numerous real-world applications are based on domain-specific text, e.g. working with financial or biomedical documents, and these applications often need to support multiple languages. However, large-scale domain-specific multilingual pretraining data for such scenarios can be difficult to obtain, due to regulations, legislation, or simply a lack of language- and domain-specific text. One solution is to tra…
Imperial College London（帝国理工学院）；University of Sheffield（谢菲尔德大学）；King’s College London（伦敦国王学院）；KTH（瑞典皇家理工学院）
A major obstacle to the development of Natural Language Processing (NLP) methods in the biomedical domain is data accessibility. This problem can be addressed by generating medical data artificially. Most previous studies have focused on the generation of short clinical text, and evaluation of the data utility has been limited. We propose a generic methodology to guide the generation of clinical text with key phrases. We use the artificial data as additional training data in two key biomedical NLP tasks: text classification and temporal relation extraction. We show that artificially generated …
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）
Language models pretrained on text from a wide variety of sources form the foundation of today's NLP. In light of the success of these broad-coverage models, we investigate whether it is still helpful to tailor a pretrained model to the domain of a target task. We present a study across four domains (biomedical and computer science publications, news, and reviews) and eight classification tasks, showing that a second phase of pretraining in-domain (domain-adaptive pretraining) leads to performance gains, under both high- and low-resource settings. Moreover, adapting to the task's unlabeled dat…
In this article, we first give an introduction to artificial intelligence and its applications in biology and medicine in Section 1. Deep learning methods are then described in Section 2. We narrow down the focus of the study on textual data in Section 3, where natural language processing and its applications in the biomedical domain are described. In Section 4, we give an introduction to explainable artificial intelligence and discuss the importance of explainability of artificial intelligence systems, especially in the biomedical domain.
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Despite recent advances in natural language processing, many statistical models for processing text perform extremely poorly under domain shift. Processing biomedical and clinical text is a critically important application area of natural language processing, for which there are few robust, practical, publicly available models. This paper describes scispaCy, a new tool for practical biomedical/scientific text processing, which heavily leverages the spaCy library. We detail the performance of two packages of models released in scispaCy and demonstrate their robustness on several tasks and datas…
BioMamba: Domain-Adaptive Biomedical Language Models
Rensselaer Polytechnic Institute（拉特格斯理工学院）；Jiaxing New Jies Thermal Power Co. Ltd.（嘉兴新捷热电有限公司）；North University of China（北方大学）；Zhejiang University（浙江大学）；IBM Research（IBM研究院）；Nanjing University（南京大学）
The complexity of sentences characteristic to biomedical articles poses a challenge to natural language parsers, which are typically trained on large-scale corpora of non-technical text. We propose a text simplification process, bioSimplify, that seeks to reduce the complexity of sentences in biomedical abstracts in order to improve the performance of syntactic parsers on the processed sentences. Syntactic parsing is typically one of the first steps in a text mining pipeline. Thus, any improvement in performance would have a ripple effect over all processing steps. We evaluated our method usin…
The availability of biomedical text data and advances in natural language processing (NLP) have made new applications in biomedical NLP possible. Language models trained or fine tuned using domain specific corpora can outperform general models, but work to date in biomedical NLP has been limited in terms of corpora and tasks. We present BioALBERT, a domain-specific adaptation of A Lite Bidirectional Encoder Representations from Transformers (ALBERT), trained on biomedical (PubMed and PubMed Central) and clinical (MIMIC-III) corpora and fine tuned for 6 different tasks across 20 benchmark datas…
National Center for Biotechnology Information（国家生物技术信息中心）；National Library of Medicine, National Institutes of Health（美国国立卫生研究院国家医学图书馆）
Inspired by the success of the General Language Understanding Evaluation benchmark, we introduce the Biomedical Language Understanding Evaluation (BLUE) benchmark to facilitate research in the development of pre-training language representations in the biomedicine domain. The benchmark consists of five tasks with ten datasets that cover both biomedical and clinical texts with different dataset sizes and difficulties. We also evaluate several baselines based on BERT and ELMo and find that the BERT model pre-trained on PubMed abstracts and MIMIC-III clinical notes achieves the best results. We m…
Domain adaptation of Pretrained Language Models (PTLMs) is typically achieved by unsupervised pretraining on target-domain text. While successful, this approach is expensive in terms of hardware, runtime and CO_2 emissions. Here, we propose a cheaper alternative: We train Word2Vec on target-domain text and align the resulting word vectors with the wordpiece vectors of a general-domain PTLM. We evaluate on eight biomedical Named Entity Recognition (NER) tasks and compare against the recently proposed BioBERT model. We cover over 60% of the BioBERT-BERT F1 delta, at 5% of BioBERT's CO_2 footprin…
Relation extraction is a fundamental problem in natural language processing. Most existing models are defined for relation extraction in the general domain. However, their performance on specific domains (e.g., biomedicine) is yet unclear. To fill this gap, this paper carries out an empirical study on relation extraction in biomedical research articles. Specifically, we consider both sentence-level and document-level relation extraction, and run a few state-of-the-art methods on several benchmark datasets. Our results show that (1) current document-level relation extraction methods have strong…
Named entity disambiguation (NED), which involves mapping textual mentions to structured entities, is particularly challenging in the medical domain due to the presence of rare entities. Existing approaches are limited by the presence of coarse-grained structural resources in biomedical knowledge bases as well as the use of training datasets that provide low coverage over uncommon resources. In this work, we address these issues by proposing a cross-domain data integration method that transfers structural knowledge from a general text knowledge base to the medical domain. We utilize our integr…
