Deep Contextualized Biomedical Abbreviation Expansion
Abstract
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.
Recommended Citation
Q. Jin et al., "Deep Contextualized Biomedical Abbreviation Expansion," Proceedings of the 18th BioNLP Workshop and Shared Task (2019, Florence, Italy), pp. 88 - 96, Association for Computational Linguistics, Jan 2019.
The definitive version is available at https://doi.org/10.18653/v1/w19-5010
Meeting Name
18th BioNLP Workshop and Shared Task (2019: Aug. 1, Florence, Italy)
Department(s)
Engineering Management and Systems Engineering
Second Department
Biological Sciences
Research Center/Lab(s)
Center for High Performance Computing Research
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2019 Association for Computational Linguistics, All rights reserved.
Publication Date
01 Jan 2019