Sparse Fuzzy Attention for Structured Sentiment Analysis
This work addresses a domain-specific issue in structured sentiment analysis, offering incremental improvements for parsing tasks in natural language processing.
The paper tackled the problem of sparse dependency edges hindering parser performance in structured sentiment analysis by proposing a sparse and fuzzy attention scorer with pooling layers, which improved parser performance and set a new state-of-the-art on the task.
Attention scorers have achieved success in parsing tasks like semantic and syntactic dependency parsing. However, in tasks modeled into parsing, like structured sentiment analysis, "dependency edges" are very sparse which hinders parser performance. Thus we propose a sparse and fuzzy attention scorer with pooling layers which improves parser performance and sets the new state-of-the-art on structured sentiment analysis. We further explore the parsing modeling on structured sentiment analysis with second-order parsing and introduce a novel sparse second-order edge building procedure that leads to significant improvement in parsing performance.