Universal Reordering via Linguistic Typology

Joachim Daiber, Milos Stanojevic, Khalil Sima'an

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

Abstract

In this paper we explore the novel idea of building a single universal reordering model from English to a large number of target languages. To build this model we exploit typological features of word order for a large number of target languages together with source (English) syntactic features and we train this model on a single combined parallel corpus representing all (22) involved language pairs. We contribute experimental evidence for the usefulness of linguistically defined typological features for building such a model. When the universal reordering model is used for preordering followed by monotone translation (no reordering inside the decoder), our experiments show that this pipeline gives comparable or improved translation performance with a phrase-based baseline for a large number of language pairs (12 out of 22) from diverse language families.
Original languageEnglish
Title of host publicationProceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Place of PublicationOsaka, Japan
PublisherThe COLING 2016 Organizing Committee
Pages3167-3176
Number of pages10
Publication statusPublished - 30 Nov 2016
Event26th International Conference on Computational Linguistics - Osaka, Japan
Duration: 11 Dec 201616 Dec 2016
http://coling2016.anlp.jp/

Conference

Conference26th International Conference on Computational Linguistics
Abbreviated titleCOLING 2016
CountryJapan
CityOsaka
Period11/12/1616/12/16
Internet address

Fingerprint Dive into the research topics of 'Universal Reordering via Linguistic Typology'. Together they form a unique fingerprint.

Cite this