Enhancing biomedical word embeddings by retrofitting to verb clusters

Billy Chiu, Simon Baker, Martha Palmer, Anna Korhonen


Abstract
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.
Anthology ID:
W19-5014
Volume:
Proceedings of the 18th BioNLP Workshop and Shared Task
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Dina Demner-Fushman, Kevin Bretonnel Cohen, Sophia Ananiadou, Junichi Tsujii
Venue:
BioNLP
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
125–134
Language:
URL:
https://aclanthology.org/W19-5014
DOI:
10.18653/v1/W19-5014
Bibkey:
Cite (ACL):
Billy Chiu, Simon Baker, Martha Palmer, and Anna Korhonen. 2019. Enhancing biomedical word embeddings by retrofitting to verb clusters. In Proceedings of the 18th BioNLP Workshop and Shared Task, pages 125–134, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Enhancing biomedical word embeddings by retrofitting to verb clusters (Chiu et al., BioNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-5014.pdf
Code
 cambridgeltl/retrofitted-bio-embeddings
Data
HOC