Parsing All: Syntax and Semantics, Dependencies and Spans
This work addresses a gap in natural language processing by enabling bidirectional interaction between syntactic and semantic parsing, which is incremental but improves performance across multiple formalisms.
The paper tackles the problem of jointly modeling syntactic and semantic parsing across both span and dependency representations, demonstrating that syntax and semantics can mutually benefit each other. The single model achieves state-of-the-art or competitive results on Propbank and Penn Treebank benchmarks.
Both syntactic and semantic structures are key linguistic contextual clues, in which parsing the latter has been well shown beneficial from parsing the former. However, few works ever made an attempt to let semantic parsing help syntactic parsing. As linguistic representation formalisms, both syntax and semantics may be represented in either span (constituent/phrase) or dependency, on both of which joint learning was also seldom explored. In this paper, we propose a novel joint model of syntactic and semantic parsing on both span and dependency representations, which incorporates syntactic information effectively in the encoder of neural network and benefits from two representation formalisms in a uniform way. The experiments show that semantics and syntax can benefit each other by optimizing joint objectives. Our single model achieves new state-of-the-art or competitive results on both span and dependency semantic parsing on Propbank benchmarks and both dependency and constituent syntactic parsing on Penn Treebank.