Part-of-speech based label update network for aspect sentiment triplet extraction

Abstract

Aspect sentiment triplet analysis (ASTE) is a nuanced task that entails the extraction of all triplets from a user comment, where each triplet consist of an aspect term, an opinion term, and the associated sentiment polarity of the aspect term. Recent research has brought forth a boundary-driven table-filling approach that adeptly tackles the persistent issues of inconsistent relationships and boundary insensitivity found in prior methods, but the improvement in performance is somewhat limited because this method overlook the wealth of information encapsulated within each word present in the sentence. To overcome these limitations, this study proposes a novel Part-of-speech Based Label Update Network (PBLUN) for aspect sentiment triplet extraction. Specifically, a POS-based label update module integrated with aspect term extraction (ATE) and opinion term extraction (OTE) tasks is devised to discern the existence of aspect or opinion words within the set adjacent search domain and update their labels. In addition, the proposed model leverages biaffine attention network to extract probability distribution denoting various relationships between words and effectively combine them with relation-level representation. Experiments conducted on four benchmark datasets have conclusively demonstrated the advantages of our proposed method when compared to strong baseline models.

Keywords

• Natural language processing
• Aspect-based sentiment analysis
• Aspect sentiment triplet extraction
• Part-of-speech
• Graph convolutional network
• Biaffine attention network