Work

Unsupervised AMR-Dependency Parse Alignment

Year: 2017

Type: conference-paper

Abstract: In this paper, we introduce an Abstract Meaning Representation (AMR) to Dependency Parse aligner.Alignment is a preliminary step for AMR parsing, and our aligner improves current AMR parser performance.Our aligner involves several different features, including named entity tags and semantic role labels, and uses Expectation-Maximization training.Results show that our aligner reaches an 87.1% F-Score score with the experimental data, and enhances AMR parsing.

DOI: 10.18653/v1/e17-1053

Authors: Wei-Te Chen, Martha Palmer

Institution: University of Colorado Boulder

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Funders: National Science Foundation, Johns Hopkins University

Awards: RI: Large: Collaborative Research: Richer Representations for Machine Translation, PIRE: Investigation of Meaning Representations in Language Understanding for Machine Translation Systems

OpenAlex ID: W2741008457