SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics
This work addresses sentiment analysis for natural language processing applications, but it is incremental as it builds on existing BERT architectures with specific modifications.
The paper tackled the problem of capturing compositional sentiment semantics by proposing SentiBERT, a BERT variant that uses contextualized representations with binary constituency parse trees, achieving competitive performance on phrase-level sentiment classification and demonstrating transferability to other tasks like emotion classification.
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.