Carnegie Mellon University
Browse
file.pdf (172.44 kB)

Supersense Tagging for Arabic: the MT-in-the-Middle Attack

Download (172.44 kB)
journal contribution
posted on 2013-06-01, 00:00 authored by Nathan Schneider, Behrang Mohit, Chris Dyer, Kemal OflazerKemal Oflazer, Noah A. Smith

We consider the task of tagging Arabic nouns with WordNet supersenses. Three approaches are evaluated. The first uses an expertcrafted but limited-coverage lexicon, Arabic WordNet, and heuristics. The second uses unsupervised sequence modeling. The third and most successful approach uses machine translation to translate the Arabic into English, which is automatically tagged with English supersenses, the results of which are then projected back into Arabic. Analysis shows gains and remaining obstacles in four Wikipedia topical domains.

History

Publisher Statement

Copyright 2013 ACL

Date

2013-06-01

Usage metrics

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC