Verbs play a fundamental role in many biomed-ical tasks and applications such as relation and event extraction. We hypothesize that performance on many downstream tasks can be improved by aligning the input pretrained embeddings according to semantic verb classes.In this work, we show that by using semantic clusters for verbs, a large lexicon of verbclasses derived from biomedical literature, weare able to improve the performance of common pretrained embeddings in downstream tasks by retrofitting them to verb classes. We present a simple and computationally efficient approach using a widely-available “off-the-shelf” retrofitting algorithm to align pretrained embeddings according to semantic verb clusters. We achieve state-of-the-art results on text classification and relation extraction tasks.
|Title of host publication||Proceedings of the 18th BioNLP Workshop and Shared Task|
|Editors||Dina DEMNER-FUSHMAN, Kevin Bretonnel COHEN, Sophia ANANIADOU, Junichi TSUJII|
|Publisher||Association for Computational Linguistics (ACL)|
|Number of pages||10|
|Publication status||Published - Aug 2019|
|Event||18th BioNLP Workshop and Shared Task - Florence, Italy|
Duration: 1 Aug 2019 → 1 Aug 2019
|Conference||18th BioNLP Workshop and Shared Task|
|Period||1/08/19 → 1/08/19|
Bibliographical noteThis work is supported by the Medical Research Council [grant number MR/M013049/1], the ERC Consolidator Grant LEXICAL [grant number:648909], the ESRC Doctoral Fellowship [grant number: ES/J500033/1] and the Defense Advanced Research Projects Agency [DARPA 15-18-CwCFP-032].
We would like to thank our reviewers for their constructive feedback. We are very grateful to Tyler Griffiths for helping with proofreading and typesetting this paper.