Abstract
Meaning of words constantly change given the events in modern civilization. Large Language Models use word embeddings, which are often static and thus cannot cope with this semantic change. Thus, it is important to resolve ambiguity in word meanings. This paper is an effort in this direction, where we explore methods for word sense disambiguation for the EvoNLP shared task. We conduct rigorous ablations for two solutions to this problem. We see that an approach using time-aware language models helps this task. Furthermore, we explore possible future directions to this problem.- Anthology ID:
- 2022.evonlp-1.8
- Volume:
- Proceedings of the First Workshop on Ever Evolving NLP (EvoNLP)
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates (Hybrid)
- Editors:
- Francesco Barbieri, Jose Camacho-Collados, Bhuwan Dhingra, Luis Espinosa-Anke, Elena Gribovskaya, Angeliki Lazaridou, Daniel Loureiro, Leonardo Neves
- Venue:
- EvoNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 55–60
- Language:
- URL:
- https://aclanthology.org/2022.evonlp-1.8
- DOI:
- 10.18653/v1/2022.evonlp-1.8
- Cite (ACL):
- Mihir Godbole, Parth Dandavate, and Aditya Kane. 2022. Temporal Word Meaning Disambiguation using TimeLMs. In Proceedings of the First Workshop on Ever Evolving NLP (EvoNLP), pages 55–60, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- Temporal Word Meaning Disambiguation using TimeLMs (Godbole et al., EvoNLP 2022)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2022.evonlp-1.8.pdf