SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics

Da Yin, Tao Meng, Kai-Wei Chang


Abstract
We propose SentiBERT, a variant of BERT that effectively captures compositional sentiment semantics. The model incorporates contextualized representation with binary constituency parse tree to capture semantic composition. Comprehensive experiments demonstrate that SentiBERT achieves competitive performance on phrase-level sentiment classification. We further demonstrate that the sentiment composition learned from the phrase-level annotations on SST can be transferred to other sentiment analysis tasks as well as related tasks, such as emotion classification tasks. Moreover, we conduct ablation studies and design visualization methods to understand SentiBERT. We show that SentiBERT is better than baseline approaches in capturing negation and the contrastive relation and model the compositional sentiment semantics.
Anthology ID:
2020.acl-main.341
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3695–3706
Language:
URL:
https://aclanthology.org/2020.acl-main.341
DOI:
10.18653/v1/2020.acl-main.341
Bibkey:
Cite (ACL):
Da Yin, Tao Meng, and Kai-Wei Chang. 2020. SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3695–3706, Online. Association for Computational Linguistics.
Cite (Informal):
SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics (Yin et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.341.pdf
Video:
 http://slideslive.com/38928884
Code
 WadeYin9712/SentiBERT +  additional community code
Data
SSTSST-2SST-5