TY - GEN
T1 - Opinion-based Relational Pivoting for Cross-domain Aspect Term Extraction
AU - Klein, Ayal
AU - Pereg, Oren
AU - Korat, Daniel
AU - Lal, Vasudev
AU - Wasserblat, Moshe
AU - Dagan, Ido
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85137654180&partnerID=8YFLogxK
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85137654180
T3 - WASSA 2022 - 12th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop
SP - 104
EP - 112
BT - WASSA 2022 - 12th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop
A2 - Barnes, Jeremy
A2 - De Clercq, Orphee
A2 - Barriere, Valentin
A2 - Tafreshi, Shabnam
A2 - Alqahtani, Sawsan
A2 - Sedoc, Joao
A2 - Klinger, Roman
A2 - Balahur, Alexandra
PB - Association for Computational Linguistics (ACL)
T2 - 12th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2022
Y2 - 26 May 2022
ER -