Coordination Boundary Identification without Labeled Data for Compound Terms Disambiguation

Yuya Sawada, Takashi Wada, Takayoshi Shibahara, Hiroki Teranishi, Shuhei Kondo, Hiroyuki Shindo, Taro Watanabe, Yuji Matsumoto


Abstract
We propose a simple method for nominal coordination boundary identification. As the main strength of our method, it can identify the coordination boundaries without training on labeled data, and can be applied even if coordination structure annotations are not available. Our system employs pre-trained word embeddings to measure the similarities of words and detects the span of coordination, assuming that conjuncts share syntactic and semantic similarities. We demonstrate that our method yields good results in identifying coordinated noun phrases in the GENIA corpus and is comparable to a recent supervised method for the case when the coordinator conjoins simple noun phrases.
Anthology ID:
2020.coling-main.271
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:
3043–3049
Language:
URL:
https://aclanthology.org/2020.coling-main.271
DOI:
10.18653/v1/2020.coling-main.271
Bibkey:
Cite (ACL):
Yuya Sawada, Takashi Wada, Takayoshi Shibahara, Hiroki Teranishi, Shuhei Kondo, Hiroyuki Shindo, Taro Watanabe, and Yuji Matsumoto. 2020. Coordination Boundary Identification without Labeled Data for Compound Terms Disambiguation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3043–3049, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Coordination Boundary Identification without Labeled Data for Compound Terms Disambiguation (Sawada et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.271.pdf