Towards Better Context-aware Lexical Semantics:Adjusting Contextualized Representations through Static Anchors

Qianchu Liu, Diana McCarthy, Anna Korhonen


Abstract
One of the most powerful features of contextualized models is their dynamic embeddings for words in context, leading to state-of-the-art representations for context-aware lexical semantics. In this paper, we present a post-processing technique that enhances these representations by learning a transformation through static anchors. Our method requires only another pre-trained model and no labeled data is needed. We show consistent improvement in a range of benchmark tasks that test contextual variations of meaning both across different usages of a word and across different words as they are used in context. We demonstrate that while the original contextual representations can be improved by another embedding space from both contextualized and static models, the static embeddings, which have lower computational requirements, provide the most gains.
Anthology ID:
2020.emnlp-main.333
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4066–4075
Language:
URL:
https://aclanthology.org/2020.emnlp-main.333
DOI:
10.18653/v1/2020.emnlp-main.333
Bibkey:
Cite (ACL):
Qianchu Liu, Diana McCarthy, and Anna Korhonen. 2020. Towards Better Context-aware Lexical Semantics:Adjusting Contextualized Representations through Static Anchors. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4066–4075, Online. Association for Computational Linguistics.
Cite (Informal):
Towards Better Context-aware Lexical Semantics:Adjusting Contextualized Representations through Static Anchors (Liu et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2020.emnlp-main.333.pdf
Video:
 https://slideslive.com/38938898