A Multi-task Learning Framework for Opinion Triplet Extraction
This work addresses a gap in ABSA by enabling more comprehensive sentiment analysis through triplet extraction, though it is incremental as it builds on existing ABSA methods.
The paper tackles the problem of Aspect-based Sentiment Analysis by proposing a multi-task learning framework for opinion triplet extraction, which jointly extracts aspect and opinion terms and parses their sentiment dependencies, achieving significant performance improvements over strong baselines on four SemEval benchmarks.
The state-of-the-art Aspect-based Sentiment Analysis (ABSA) approaches are mainly based on either detecting aspect terms and their corresponding sentiment polarities, or co-extracting aspect and opinion terms. However, the extraction of aspect-sentiment pairs lacks opinion terms as a reference, while co-extraction of aspect and opinion terms would not lead to meaningful pairs without determining their sentiment dependencies. To address the issue, we present a novel view of ABSA as an opinion triplet extraction task, and propose a multi-task learning framework to jointly extract aspect terms and opinion terms, and simultaneously parses sentiment dependencies between them with a biaffine scorer. At inference phase, the extraction of triplets is facilitated by a triplet decoding method based on the above outputs. We evaluate the proposed framework on four SemEval benchmarks for ASBA. The results demonstrate that our approach significantly outperforms a range of strong baselines and state-of-the-art approaches.