Exploring Neural Methods for Parsing Discourse Representation Structures

TL;DR

This paper introduces a neural sequence-to-sequence parser that effectively generates Discourse Representation Structures from English sentences, surpassing traditional methods in accuracy and robustness.

Contribution

It presents a novel neural approach for DRS parsing, including techniques for well-formedness verification and improved training strategies.

Findings

Neural parser outperforms traditional DRS parsers.

Character-based input yields better results than word-based.

Using De Bruijn-indices enhances parser performance.

Abstract

Neural methods have had several recent successes in semantic parsing, though they have yet to face the challenge of producing meaning representations based on formal semantics. We present a sequence-to-sequence neural semantic parser that is able to produce Discourse Representation Structures (DRSs) for English sentences with high accuracy, outperforming traditional DRS parsers. To facilitate the learning of the output, we represent DRSs as a sequence of flat clauses and introduce a method to verify that produced DRSs are well-formed and interpretable. We compare models using characters and words as input and see (somewhat surprisingly) that the former performs better than the latter. We show that eliminating variable names from the output using De Bruijn-indices increases parser performance. Adding silver training data boosts performance even further.