Paper: Bitext Dependency Parsing with Bilingual Subtree Constraints

ACL ID P10-1003
Title Bitext Dependency Parsing with Bilingual Subtree Constraints
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2010

This paper proposes a dependency parsing method that uses bilingual constraints to improve the accuracy of parsing bilingual texts (bitexts). In our method, a target- side tree fragment that corresponds to a source-side tree fragment is identified via word alignment and mapping rules that are automatically learned. Then it is ver- ified by checking the subtree list that is collected from large scale automatically parseddataonthetargetside. Ourmethod, thus, requires gold standard trees only on the source side of a bilingual corpus in the training phase, unlike the joint parsing model, which requires gold standard trees on the both sides. Compared to the re- ordering constraint model, which requires the same training data as ours, our method achievedhigheraccuracybecauseofricher bilingual co...