Temporal Word Meaning Disambiguation using TimeLMs
Published in EMNLP 2022 EvoNLP workshop, 2022
Recommended citation: Godbole, M., Dandavate, P. and Kane, A., 2022. Temporal Word Meaning Disambiguation using TimeLMs. arXiv preprint arXiv:2210.08207. https://arxiv.org/abs/2210.08207
Meaning of words constantly changes 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.
If you find our paper useful in your research, please consider citing:
@misc{https://doi.org/10.48550/arxiv.2210.08207,
doi = {10.48550/ARXIV.2210.08207},
url = {https://arxiv.org/abs/2210.08207},
author = {Godbole, Mihir and Dandavate, Parth and Kane, Aditya},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Temporal Word Meaning Disambiguation using TimeLMs},
publisher = {arXiv},
year = {2022},
copyright = {arXiv.org perpetual, non-exclusive license}
}