Work

Spanning Tree Methods for Discriminative Training of Dependency Parsers

Year: 2006

Type: article

Abstract: Untyped dependency parsing can be viewed as the problem of finding maximum spanning trees (MSTs) in directed graphs. Using this representation, the Eisner (1996) parsing algorithm is sufficient for searching the space of projective trees. More importantly, the representation is extended naturally to non-projective parsing using Chu-Liu-Edmonds (Chu and Liu, 1965; Edmonds, 1967) MST algorithm. These efficient parse search methods support large-margin discriminative training methods for learning dependency parsers. We evaluate these methods experimentally on the English and Czech treebanks. 1

Source: ScholarlyCommons (University of Pennsylvania)

Authors: Ryan McDonald, Koby Crammer, Fernando C. N. Pereira

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Awards: ITR: Mining the Bibliome -- Information Extraction from the Biomedical Literature, ITR: Language, Learning, and Modeling Biological Sequences, ITR: Collaborative Research: (ACS+NHS)-(dmc+soc): Machine Learning for Sequences and Structured Data: Tools for Non-Experts

OpenAlex ID: W122473599

FWCI: 2.823

Cites: 41

Cited by: 16

Related to: 10