Dependency Grammar Induction via Bitext Projection Constraints

Loading...
Thumbnail Image
Penn collection
Lab Papers (GRASP)
Degree type
Discipline
Subject
Funder
Grant number
License
Copyright date
Distributor
Related resources
Contributor
Abstract

Broad-coverage annotated treebanks necessary to train parsers do not exist for many resource-poor languages. The wide availability of parallel text and accurate parsers in English has opened up the possibility of grammar induction through partial transfer across bitext. We consider generative and discriminative models for dependency grammar induction that use word-level alignments and a source language parser (English) to constrain the space of possible target trees. Unlike previous approaches, our framework does not require full projected parses, allowing partial, approximate transfer through linear expectation constraints on the space of distributions over trees. We consider several types of constraints that range from generic dependency conservation to language-specific annotation rules for auxiliary verb analysis. We evaluate our approach on Bulgarian and Spanish CoNLL shared task data and show that we consistently outperform unsupervised methods and can outperform supervised learning for limited training data.

Advisor
Date of presentation
2009-08-02
Conference name
Lab Papers (GRASP)
Conference dates
2023-05-17T03:10:51.000
Conference location
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Reprinted from: Dependency Grammar Induction via Bitext Projection Constraints. Kuzman Ganchev, Jennifer Gillenwater and Ben Taskar. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, Singapore, Aug. 2-7, 2009. pp. 369-377.
Recommended citation
Collection