CLDec 29, 2020

DRS at MRP 2020: Dressing up Discourse Representation Structures as Graphs

arXiv:2012.14837v1994 citations
AI Analysis

This work provides a method for integrating DRT into graph-based semantic parsing frameworks, which is significant for researchers working on unified models for natural language meaning representation.

This paper describes a procedure to convert Discourse Representation Structures (DRSs) from Discourse Representation Theory (DRT) into directed labeled graphs. This conversion allowed DRT to be included as a new framework in the 2020 shared task on Cross-Framework and Cross-Lingual Meaning Representation Parsing, facilitating unified models across semantic graph frameworks.

Discourse Representation Theory (DRT) is a formal account for representing the meaning of natural language discourse. Meaning in DRT is modeled via a Discourse Representation Structure (DRS), a meaning representation with a model-theoretic interpretation, which is usually depicted as nested boxes. In contrast, a directed labeled graph is a common data structure used to encode semantics of natural language texts. The paper describes the procedure of dressing up DRSs as directed labeled graphs to include DRT as a new framework in the 2020 shared task on Cross-Framework and Cross-Lingual Meaning Representation Parsing. Since one of the goals of the shared task is to encourage unified models for several semantic graph frameworks, the conversion procedure was biased towards making the DRT graph framework somewhat similar to other graph-based meaning representation frameworks.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes