Revisiting Structured Sentiment Analysis as Latent Dependency Graph Parsing
This work improves sentiment analysis for natural language processing by addressing a specific bottleneck in span representation, though it is incremental in nature.
The paper tackled the problem of structured sentiment analysis by addressing the neglect of internal structures in spans within bi-lexical dependency graph parsing, proposing a method that treats spans as latent subtrees and achieved new state-of-the-art results on five benchmark datasets.
Structured Sentiment Analysis (SSA) was cast as a problem of bi-lexical dependency graph parsing by prior studies. Multiple formulations have been proposed to construct the graph, which share several intrinsic drawbacks: (1) The internal structures of spans are neglected, thus only the boundary tokens of spans are used for relation prediction and span recognition, thus hindering the model's expressiveness; (2) Long spans occupy a significant proportion in the SSA datasets, which further exacerbates the problem of internal structure neglect. In this paper, we treat the SSA task as a dependency parsing task on partially-observed dependency trees, regarding flat spans without determined tree annotations as latent subtrees to consider internal structures of spans. We propose a two-stage parsing method and leverage TreeCRFs with a novel constrained inside algorithm to model latent structures explicitly, which also takes advantages of joint scoring graph arcs and headed spans for global optimization and inference. Results of extensive experiments on five benchmark datasets reveal that our method performs significantly better than all previous bi-lexical methods, achieving new state-of-the-art.