Robust Incremental Neural Semantic Graph Parsing
This provides a robust and efficient parsing solution for natural language processing tasks requiring detailed semantic representations, though it is incremental as it builds on existing neural methods.
The authors tackled the problem of parsing sentences into linguistically-expressive semantic graphs, specifically for Minimal Recursion Semantics (MRS), by proposing a neural encoder-decoder transition-based parser that achieves 86.69% Smatch score and is an order of magnitude faster than grammar-based parsers.
Parsing sentences to linguistically-expressive semantic representations is a key goal of Natural Language Processing. Yet statistical parsing has focused almost exclusively on bilexical dependencies or domain-specific logical forms. We propose a neural encoder-decoder transition-based parser which is the first full-coverage semantic graph parser for Minimal Recursion Semantics (MRS). The model architecture uses stack-based embedding features, predicting graphs jointly with unlexicalized predicates and their token alignments. Our parser is more accurate than attention-based baselines on MRS, and on an additional Abstract Meaning Representation (AMR) benchmark, and GPU batch processing makes it an order of magnitude faster than a high-precision grammar-based parser. Further, the 86.69% Smatch score of our MRS parser is higher than the upper-bound on AMR parsing, making MRS an attractive choice as a semantic representation.