Work

Dealing with Co-reference in Neural Semantic Parsing

Year: 2017

Type: conference-paper

Abstract: Linguistic phenomena like pronouns, control constructions, or co-reference give rise to co-indexed variables in meaning representations. We review three different methods for dealing with co-indexed variables in the output of neural semantic parsing of abstract meaning representations: (a) copying concepts during training and restoring co-indexation in a post-processing step; (b) explicit indexing of co-indexation; and (c) using absolute paths to designate co-indexing. The second method gives the best results and outperforms the baseline by 2.9 F-score points.

Source: University of Groningen research database (University of Groningen / Centre for Information Technology)

Authors: Rik van Noord, Johan Bos

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Nvidia, Rijksuniversiteit Groningen, Nederlandse Organisatie voor Wetenschappelijk Onderzoek

Awards: G1833903074, G2010355708, G5801408398

OpenAlex ID: W2766069626

FWCI: 1.778

Cites: 10

Cited by: 17

Related to: 20