Enhancing Aspect Term Extraction with Soft Prototypes

Zhuang Chen, Tieyun Qian


Abstract
Aspect term extraction (ATE) aims to extract aspect terms from a review sentence that users have expressed opinions on. Existing studies mostly focus on designing neural sequence taggers to extract linguistic features from the token level. However, since the aspect terms and context words usually exhibit long-tail distributions, these taggers often converge to an inferior state without enough sample exposure. In this paper, we propose to tackle this problem by correlating words with each other through soft prototypes. These prototypes, generated by a soft retrieval process, can introduce global knowledge from internal or external data and serve as the supporting evidence for discovering the aspect terms. Our proposed model is a general framework and can be combined with almost all sequence taggers. Experiments on four SemEval datasets show that our model boosts the performance of three typical ATE methods by a large margin.
Anthology ID:
2020.emnlp-main.164
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:
2107–2117
Language:
URL:
https://aclanthology.org/2020.emnlp-main.164
DOI:
10.18653/v1/2020.emnlp-main.164
Bibkey:
Cite (ACL):
Zhuang Chen and Tieyun Qian. 2020. Enhancing Aspect Term Extraction with Soft Prototypes. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2107–2117, Online. Association for Computational Linguistics.
Cite (Informal):
Enhancing Aspect Term Extraction with Soft Prototypes (Chen & Qian, EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.164.pdf
Video:
 https://slideslive.com/38938818