An Evaluation Method for Diachronic Word Sense Induction

Ashjan Alsulaimani, Erwan Moreau, Carl Vogel


Abstract
The task of Diachronic Word Sense Induction (DWSI) aims to identify the meaning of words from their context, taking the temporal dimension into account. In this paper we propose an evaluation method based on large-scale time-stamped annotated biomedical data, and a range of evaluation measures suited to the task. The approach is applied to two recent DWSI systems, thus demonstrating its relevance and providing an in-depth analysis of the models.
Anthology ID:
2020.findings-emnlp.284
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3171–3180
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.284
DOI:
10.18653/v1/2020.findings-emnlp.284
Bibkey:
Cite (ACL):
Ashjan Alsulaimani, Erwan Moreau, and Carl Vogel. 2020. An Evaluation Method for Diachronic Word Sense Induction. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3171–3180, Online. Association for Computational Linguistics.
Cite (Informal):
An Evaluation Method for Diachronic Word Sense Induction (Alsulaimani et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.284.pdf
Optional supplementary material:
 2020.findings-emnlp.284.OptionalSupplementaryMaterial.zip
Video:
 https://slideslive.com/38940034
Code
 ashjanalsulaimani/dwsi-eval