Target Word Masking for Location Metonymy Resolution

Haonan Li, Maria Vasardani, Martin Tomko, Timothy Baldwin


Abstract
Existing metonymy resolution approaches rely on features extracted from external resources like dictionaries and hand-crafted lexical resources. In this paper, we propose an end-to-end word-level classification approach based only on BERT, without dependencies on taggers, parsers, curated dictionaries of place names, or other external resources. We show that our approach achieves the state-of-the-art on 5 datasets, surpassing conventional BERT models and benchmarks by a large margin. We also show that our approach generalises well to unseen data.
Anthology ID:
2020.coling-main.330
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
3696–3707
Language:
URL:
https://aclanthology.org/2020.coling-main.330
DOI:
10.18653/v1/2020.coling-main.330
Bibkey:
Cite (ACL):
Haonan Li, Maria Vasardani, Martin Tomko, and Timothy Baldwin. 2020. Target Word Masking for Location Metonymy Resolution. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3696–3707, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Target Word Masking for Location Metonymy Resolution (Li et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.330.pdf
Code
 haonan-li/TWM-metonymy-resolution