Rich morphology generation using statistical machine translation

Ahmed El Kholy, Nizar Habash

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present an approach for generation of morphologically rich languages using statistical machine translation. Given a sequence of lemmas and any subset of morphological features, we produce the inflected word forms. Testing on Arabic, a morphologically rich language, our models can reach 92.1% accuracy starting only with lemmas, and 98.9% accuracy if all the gold features are provided.

Original languageEnglish (US)
Title of host publicationINLG 2012 - Proceedings of the 7th International Natural Language Generation Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages90-94
Number of pages5
ISBN (Electronic)9781937284237
StatePublished - 2012
Event7th International Natural Language Generation Conference, INLG 2012 - Utica, United States
Duration: May 30 2012Jun 1 2012

Publication series

NameINLG 2012 - Proceedings of the 7th International Natural Language Generation Conference

Conference

Conference7th International Natural Language Generation Conference, INLG 2012
CountryUnited States
CityUtica
Period5/30/126/1/12

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'Rich morphology generation using statistical machine translation'. Together they form a unique fingerprint.

Cite this