Cross-lingual word embeddings for low-resource language modeling

Oliver Adams, Adam Makarucha, Graham Neubig, Steven Bird, Trevor Cohn

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in Proceedingspeer-review

2 Downloads (Pure)

Abstract

Most languages have no established writing system and minimal written records. However, textual data is essential for natural language processing, and particularly important for training language models to support speech recognition. Even in cases where text data is missing, there are some languages for which bilingual lexicons are available, since creating lexicons is a fundamental task of documentary linguistics. We investigate the use of such lexicons to improve language models when textual training data is limited to as few as a thousand sentences. The method involves learning cross-lingual word embeddings as a preliminary step in training monolingual language models. Results across a number of languages show that language models are improved by this pre-training. Application to Yongning Na, a threatened language, highlights challenges in deploying the approach in real low-resource environments.

Original languageEnglish
Title of host publicationProceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics
Subtitle of host publicationVolume 1, Long Papers
EditorsMirella Lapata, Phil Blunsom, Alexander Koller
Place of PublicationPennsylvania
PublisherAssociation for Computational Linguistics (ACL)
Pages937-947
Number of pages11
Volume1
ISBN (Electronic)9781510838604
DOIs
Publication statusPublished - 1 Jul 2017
Externally publishedYes
Event15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Valencia, Spain
Duration: 3 Apr 20177 Apr 2017

Conference

Conference15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017
Country/TerritorySpain
CityValencia
Period3/04/177/04/17

Fingerprint

Dive into the research topics of 'Cross-lingual word embeddings for low-resource language modeling'. Together they form a unique fingerprint.

Cite this