Opinion-based Relational Pivoting for Cross-domain Aspect Term Extraction

Ayal Klein, Oren Pereg, Daniel Korat, Vasudev Lal, Moshe Wasserblat, Ido Dagan


Abstract
Domain adaptation methods often exploit domain-transferable input features, a.k.a. pivots. The task of Aspect and Opinion Term Extraction presents a special challenge for domain transfer: while opinion terms largely transfer across domains, aspects change drastically from one domain to another (e.g. from restaurants to laptops). In this paper, we investigate and establish empirically a prior conjecture, which suggests that the linguistic relations connecting opinion terms to their aspects transfer well across domains and therefore can be leveraged for cross-domain aspect term extraction. We present several analyses supporting this conjecture, via experiments with four linguistic dependency formalisms to represent relation patterns. Subsequently, we present an aspect term extraction method that drives models to consider opinion–aspect relations via explicit multitask objectives. This method provides significant performance gains, even on top of a prior state-of-the-art linguistically-informed model, which are shown in analysis to stem from the relational pivoting signal.
Anthology ID:
2022.wassa-1.11
Volume:
Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Jeremy Barnes, Orphée De Clercq, Valentin Barriere, Shabnam Tafreshi, Sawsan Alqahtani, João Sedoc, Roman Klinger, Alexandra Balahur
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
104–112
Language:
URL:
https://aclanthology.org/2022.wassa-1.11
DOI:
10.18653/v1/2022.wassa-1.11
Bibkey:
Cite (ACL):
Ayal Klein, Oren Pereg, Daniel Korat, Vasudev Lal, Moshe Wasserblat, and Ido Dagan. 2022. Opinion-based Relational Pivoting for Cross-domain Aspect Term Extraction. In Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, pages 104–112, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Opinion-based Relational Pivoting for Cross-domain Aspect Term Extraction (Klein et al., WASSA 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2022.wassa-1.11.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-1/2022.wassa-1.11.mp4