We introduce BIOMRC, a large-scale cloze-style biomedical MRC dataset. Care was taken to reduce noise, compared to the previous BIOREAD dataset of Pappas et al. (2018). Experiments show that simple heuristics do not perform well on the new dataset, and that two neural MRC models that had been tested on BIOREAD perform much better on BIOMRC, indicating that the new dataset is indeed less noisy or at least that its task is more feasible. Non-expert human performance is also higher on the new dataset compared to BIOREAD, and biomedical experts perform even better. We also introduce a new BERT-based MRC model, the best version of which substantially outperforms all other methods tested, reaching or surpassing the accuracy of biomedical experts in some experiments. We make the new dataset available in three different sizes, also releasing our code, and providing a leaderboard.
Biomedical Question Answering aims to obtain an answer to the given question from the biomedical domain. Due to its high requirement of biomedical domain knowledge, it is difficult for the model to learn domain knowledge from limited training data. We propose a contextual embedding method that combines open-domain QA model \aoa and \biobert model pre-trained on biomedical domain data. We adopt unsupervised pre-training on large biomedical corpus and supervised fine-tuning on biomedical question answering dataset. Additionally, we adopt an MLP-based model weighting layer to automatically exploi…
University of Tennessee（田纳西大学）；Oak Ridge National Laboratory（橡树岭国家实验室）
Biomedical machine reading comprehension (biomedical-MRC) aims to comprehend complex biomedical narratives and assist healthcare professionals in retrieving information from them. The high performance of modern neural network-based MRC systems depends on high-quality, large-scale, human-annotated training datasets. In the biomedical domain, a crucial challenge in creating such datasets is the requirement for domain knowledge, inducing the scarcity of labeled data and the need for transfer learning from the labeled general-purpose (source) domain to the biomedical (target) domain. However, ther…
Dalian University of Technology（大连理工大学）；Beijing Institute of Health Administration and Medical Information（北京卫生健康经济研究和医学信息研究所）
Recognition of biomedical entities from literature is a challenging research focus, which is the foundation for extracting a large amount of biomedical knowledge existing in unstructured texts into structured formats. Using the sequence labeling framework to implement biomedical named entity recognition (BioNER) is currently a conventional method. This method, however, often cannot take full advantage of the semantic information in the dataset, and the performance is not always satisfactory. In this work, instead of treating the BioNER task as a sequence labeling problem, we formulate it as a …
Using deep learning models on small scale datasets would result in overfitting. To overcome this problem, the process of pre-training a model and fine-tuning it to the small scale dataset has been used extensively in domains such as image processing. Similarly for question answering, pre-training and fine-tuning can be done in several ways. Commonly reading comprehension models are used for pre-training, but we show that other types of pre-training can work better. We compare two pre-training models based on reading comprehension and open domain question answering models and determine the perf…
Information Extraction (IE) from text refers to the task of extracting structured knowledge from unstructured text. The task typically consists of a series of sub-tasks such as Named Entity Recognition and Relation Extraction. Sourcing entity and relation type specific training data is a major bottleneck in domains with limited resources such as biomedicine. In this work we present a slot filling approach to the task of biomedical IE, effectively replacing the need for entity and relation-specific training data, allowing us to deal with zero-shot settings. We follow the recently proposed parad…
Adverse reaction caused by drugs is a potentially dangerous problem which may lead to mortality and morbidity in patients. Adverse Drug Event (ADE) extraction is a significant problem in biomedical research. We model ADE extraction as a Question-Answering problem and take inspiration from Machine Reading Comprehension (MRC) literature, to design our model. Our objective in designing such a model, is to exploit the local linguistic context in clinical text and enable intra-sequence interaction, in order to jointly learn to classify drug and disease entities, and to extract adverse reactions cau…
Athens University of Economics and Business（雅典经济与商业大学）；Institute for Language and Speech Processing, Research Center ‘Athena’（“雅典娜”研究中心语言与语音处理研究所）；Institute of Informatics and Telecommunications, NCSR ‘Demokritos’（国家科学研究中心“德谟克利特”信息与电信研究所）
We study the effect of seven data augmentation (da) methods in factoid question answering, focusing on the biomedical domain, where obtaining training instances is particularly difficult. We experiment with data from the BioASQ challenge, which we augment with training instances obtained from an artificial biomedical machine reading comprehension dataset, or via back-translation, information retrieval, word substitution based on word2vec embeddings, or masked language modeling, question generation, or extending the given passage with additional context. We show that da can lead to very signifi…
Training-Free BioNEL-RAG: Advancing Biomedical Entity Linking through Retrieval-Augmented Generation and Large Language Model
University of Science and Technology of China（中国科学技术大学）；School of Biomedical Engineering（生物医学工程学院）；Division of Life Sciences and Medicine（生命科学与医学部）；Department of Precision Machinery and Precision Instruments（精密机械与精密仪器系）
NEREL-BIO: A Dataset of Biomedical Abstracts Annotated with Nested Named Entities
Lomonosov Moscow State University（莫斯科罗蒙诺索夫国立大学）；Madan Bhandari University of Science and Technology（马丹·班达里科技大学）；Ural Federal University（乌拉尔联邦大学）；HSE University（高等经济大学）；Innopolis University（因诺波利斯大学）；A.P. Ershov Institute of Informatics Systems（A.P. 埃尔绍夫信息学系统研究所）；Artificial Intelligence Research Institute（人工智能研究所）；Sber AI
NTT Media Intelligence Laboratories, NTT Corporation（NTT集团NTT媒体情报实验室）
This study tackles unsupervised domain adaptation of reading comprehension (UDARC). Reading comprehension (RC) is a task to learn the capability for question answering with textual sources. State-of-the-art models on RC still do not have general linguistic intelligence; i.e., their accuracy worsens for out-domain datasets that are not used in the training. We hypothesize that this discrepancy is caused by a lack of the language modeling (LM) capability for the out-domain. The UDARC task allows models to use supervised RC training data in the source domain and only unlabeled passages in the tar…
