Multilingual Dependency Parsing: Using Machine Translated Texts instead of Parallel Corpora

This paper revisits the projection-based approach to dependency grammar induction task. Traditional cross-lingual dependency induction tasks one way or the other, depend on the existence of bitexts or target language tools such as part-of-speech (POS) taggers to obtain reasonable parsing accuracy. In this paper, we transfer dependency parsers using only approximate resources, i.e., machine translated bitexts instead of manually created bitexts. We do this by obtaining the the source side of the text from a machine translation (MT) system and then apply transfer approaches to induce parser for the target languages. We further reduce the need for the availability of labeled target language resources by using unsupervised target tagger. We show that our approach consistently outperforms unsupervised parsers by a bigger margin (8.2% absolute), and results in similar performance when compared with delexicalized transfer parsers.

[1]  Milan Straka,et al.  Stop-probability estimates computed on a large corpus improve Unsupervised Dependency Parsing , 2013, ACL.

[2]  Daniel Zeman,et al.  HamleDT: To Parse or Not to Parse? , 2012, LREC.

[3]  Slav Petrov,et al.  Multi-Source Transfer of Delexicalized Dependency Parsers , 2011, EMNLP.

[4]  James J. Masanz,et al.  LANGUAGE PROCESSING , 1998 .

[5]  Dan Klein,et al.  Syntactic Transfer Using a Bilingual Lexicon , 2012, EMNLP-CoNLL.

[6]  Jakob Uszkoreit,et al.  Cross-lingual Word Clusters for Direct Transfer of Linguistic Structure , 2012, NAACL.

[7]  Sebastian Riedel,et al.  The CoNLL 2007 Shared Task on Dependency Parsing , 2007, EMNLP.

[8]  David A. Smith,et al.  Parser Adaptation and Projection with Quasi-Synchronous Grammar Features , 2009, EMNLP.

[9]  Slav Petrov,et al.  A Universal Part-of-Speech Tagset , 2011, LREC.

[10]  Joakim Nivre,et al.  Universal Dependency Annotation for Multilingual Parsing , 2013, ACL.

[11]  Alexander Clark,et al.  Inducing Syntactic Categories by Context Distribution Clustering , 2000, CoNLL/LLL.

[12]  Fernando Pereira,et al.  Non-Projective Dependency Parsing using Spanning Tree Algorithms , 2005, HLT.

[13]  Jan Hajič,et al.  The Best of Two Worlds: Cooperation of Statistical and Rule-Based Taggers for Czech , 2007, ACL 2007.

[14]  Slav Petrov,et al.  Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections , 2011, ACL.

[15]  Philip Resnik,et al.  Bootstrapping parsers via syntactic projection across parallel texts , 2005, Natural Language Engineering.

[16]  Philip Resnik,et al.  Cross-Language Parser Adaptation between Related Languages , 2008, IJCNLP.

[17]  Zdenek Zabokrtský,et al.  Language Richness of the Web , 2012, LREC.

[18]  Phil Blunsom,et al.  Unsupervised Induction of Tree Substitution Grammars for Dependency Parsing , 2010, EMNLP.

[19]  Ben Taskar,et al.  Dependency Grammar Induction via Bitext Projection Constraints , 2009, ACL/IJCNLP.

[20]  Christopher D. Manning,et al.  Enriching the Knowledge Sources Used in a Maximum Entropy Part-of-Speech Tagger , 2000, EMNLP.

[21]  Valentin I. Spitkovsky,et al.  Breaking Out of Local Optima with Count Transforms and Model Recombination: A Study in Grammar Induction , 2013, EMNLP.

[22]  Joakim Nivre,et al.  Target Language Adaptation of Discriminative Transfer Parsers , 2013, NAACL.

[23]  Phil Blunsom,et al.  A Hierarchical Pitman-Yor Process HMM for Unsupervised Part of Speech Induction , 2011, ACL.

[24]  W. Bruce Croft,et al.  Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , 2013 .

[25]  Jonas Kuhn.  Experiments in parallel-text based grammar induction , 2004, ACL.