Low resource dependency parsing: Cross-lingual parameter sharing in a neural network parser

Long Duong, Trevor Cohn, Steven Bird, Paul Cook

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

Abstract

Training a high-accuracy dependency parser requires a large treebank. However, these are costly and time-consuming to build. We propose a learning method that needs less data, based on the observation that there are underlying shared structures across languages. We exploit cues from a different source language in order to guide the learning process. Our model saves at least half of the annotation effort to reach the same accuracy compared with using the purely supervised method.

Original languageEnglish
Title of host publicationProceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing
Subtitle of host publicationProceedings of the Conference: Volume 2: Short Papers
Place of PublicationBeijing, China
PublisherAssociation for Computational Linguistics (ACL)
Pages845-850
Number of pages6
Volume2
ISBN (Electronic)9781941643730
DOIs
Publication statusPublished - Jul 2015
Externally publishedYes
Event53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015 - Beijing, China
Duration: 26 Jul 201531 Jul 2015

Conference

Conference53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015
Country/TerritoryChina
CityBeijing
Period26/07/1531/07/15

Fingerprint

Dive into the research topics of 'Low resource dependency parsing: Cross-lingual parameter sharing in a neural network parser'. Together they form a unique fingerprint.

Cite this