Work

Combining strategies for tagging and parsing Arabic

Year: 2014

Type: conference-paper

Abstract: We describe a simple method for combiningtaggers which produces substantiallybetter performance than any of thecontributing tools. The method is verysimple, but it leads to considerable improvementsin performance: given threetaggers for Arabic whose individual accuraciesrange from 0.956 to 0.967, thecombined tagger scores 0.995–a sevenfoldreduction in the error rate whencompared to the best of the contributingtools.Given the effectiveness of this approachto combining taggers, we have investigatedits applicability to parsing. Forparsing, it seems better to take pairs ofsimilar parsers and back off to a third ifthey disagree.

Source: Arabic Natural Language Processing Workshop (WANLP)

DOI: 10.3115/v1/w14-3609

Authors: Maytham Alabbas, Allan Ramsay

Institutions: University of Basrah, University of Manchester

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Fonds National de la Recherche Luxembourg, Qatar National Research Fund

OpenAlex ID: W2251650337

FWCI: 0.393

Cites: 15

Cited by: 6

Related to: 10