We introduce PubMedQA, a novel biomedical question answering (QA) dataset collected from PubMed abstracts. The task of PubMedQA is to answer research questions with yes/no/maybe (e.g.: Do preoperative statins reduce atrial fibrillation after coronary artery bypass grafting?) using the corresponding abstracts. PubMedQA has 1k expert-annotated, 61.2k unlabeled and 211.3k artificially generated QA instances. Each PubMedQA instance is composed of (1) a question which is either an existing research article title or derived from one, (2) a context which is the corresponding abstract without its conclusion, (3) a long answer, which is the conclusion of the abstract and, presumably, answers the research question, and (4) a yes/no/maybe answer which summarizes the conclusion. PubMedQA is the first QA dataset where reasoning over biomedical research texts, especially their quantitative contents, is required to answer the questions. Our best performing model, multi-phase fine-tuning of BioBERT with long answer bag-of-word statistics as additional supervision, achieves 68.1% accuracy, compared to single human performance of 78.0% accuracy and majority-baseline of 55.2% accuracy, leaving much room for improvement. PubMedQA is publicly available at https://pubmedqa.github.io.

Contextualized word embeddings derived from pre-trained language models (LMs) show significant improvements on downstream NLP tasks. Pre-training on domain-specific corpora, such as biomedical articles, further improves their performance. In this paper, we conduct probing experiments to determine what additional information is carried intrinsically by the in-domain trained contextualized embeddings. For this we use the pre-trained LMs as fixed feature extractors and restrict the downstream task models to not have additional sequence modeling layers. We compare BERT (Devlin et al. 2018), ELMo (Peters et al., 2018), BioBERT (Lee et al., 2019) and BioELMo, a biomedical version of ELMo trained on 10M PubMed abstracts. Surprisingly, while fine-tuned BioBERT is better than BioELMo in biomedical NER and NLI tasks, as a fixed feature extractor BioELMo outperforms BioBERT in our probing tasks. We use visualization and nearest neighbor analysis to show that better encoding of entity-type and relational information leads to this superiority.

Automatic identification and expansion of ambiguous abbreviations are essential for biomedical natural language processing applications, such as information retrieval and question answering systems. In this paper, we present DEep Contextualized Biomedical Abbreviation Expansion (DECBAE) model. DECBAE automatically collects substantial and relatively clean annotated contexts for 950 ambiguous abbreviations from PubMed abstracts using a simple heuristic. Then it utilizes BioELMo to extract the contextualized features of words, and feed those features to abbreviation-specific bidirectional LSTMs, where the hidden states of the ambiguous abbreviations are used to assign the exact definitions. Our DECBAE model outperforms other baselines by large margins, achieving average accuracy of 0.961 and macro-F1 of 0.917 on the dataset. It also surpasses human performance for expanding a sample abbreviation, and remains robust in imbalanced, low-resources and clinical settings.

There are millions of articles in PubMed database. To facilitate information retrieval, curators in the National Library of Medicine (NLM) assign a set of Medical Subject Headings (MeSH) to each article. MeSH is a hierarchically-organized vocabulary, containing about 28K different concepts, covering the fields from clinical medicine to information sciences. Several automatic MeSH indexing models have been developed to improve the time-consuming and financially expensive manual annotation, including the NLM official tool – Medical Text Indexer, and the winner of BioASQ Task5a challenge – DeepMeSH. However, these models are complex and not interpretable. We propose a novel end-to-end model, AttentionMeSH, which utilizes deep learning and attention mechanism to index MeSH terms to biomedical text. The attention mechanism enables the model to associate textual evidence with annotations, thus providing interpretability at the word level. The model also uses a novel masking mechanism to enhance accuracy and speed. In the final week of BioASQ Chanllenge Task6a, we ranked 2nd by average MiF using an on-construction model. After the contest, we achieve close to state-of-the-art MiF performance of ∼ 0.684 using our final model. Human evaluations show AttentionMeSH also provides high level of interpretability, retrieving about 90% of all expert-labeled relevant words given an MeSH-article pair at 20 output.