Abstract
Attention scorers have achieved success in parsing tasks like semantic and syntactic dependency parsing. However, in tasks modeled into parsing, like structural 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 structural sentiment analysis. We further explore the parsing modeling on structural sentiment analysis with second-order parsing and introduce a novel sparse second-order edge building procedure that leads to significant improvement in parsing performance.
Abstract (translated)
URL
https://arxiv.org/abs/2109.06719