SentiBERT:一种基于转换器的组合情感语义体系结构
SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics
摘要:
我们提出了SentiBERT,一个变种的BERT,有效地捕捉成分的情感语义。该模型结合上下文表示和二元选区分析树来捕获语义组合。综合实验表明,SentiBERT在短语级情感分类上取得了有竞争力的性能。我们进一步证明了从SST上的短语级注释中学习到的情感成分可以转移到其他情感分析任务以及相关任务,例如情感分类任务。此外,我们进行消融研究和设计可视化方法来了解SentiBERT。我们表明,SentiBERT是优于基线方法在捕捉否定和对比关系和模型的成分情感语义。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。