A Linguistics-Driven Approach to Statistical Parsing for Low-Resourced Languages

Prachya BOONKWAN  Thepchai SUPNITHI  

IEICE TRANSACTIONS on Information and Systems   Vol.E98-D   No.5   pp.1045-1052
Publication Date: 2015/05/01
Publicized: 2015/01/21
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2014DAP0024
Type of Manuscript: Special Section PAPER (Special Section on Data Engineering and Information Management)
statistical parsing,  grammar induction,  language parameters,  Universal Grammar,  treebank,  

Full Text: PDF(625.5KB)>>
Buy this Article

Developing a practical and accurate statistical parser for low-resourced languages is a hard problem, because it requires large-scale treebanks, which are expensive and labor-intensive to build from scratch. Unsupervised grammar induction theoretically offers a way to overcome this hurdle by learning hidden syntactic structures from raw text automatically. The accuracy of grammar induction is still impractically low because frequent collocations of non-linguistically associable units are commonly found, resulting in dependency attachment errors. We introduce a novel approach to building a statistical parser for low-resourced languages by using language parameters as a guide for grammar induction. The intuition of this paper is: most dependency attachment errors are frequently used word orders which can be captured by a small prescribed set of linguistic constraints, while the rest of the language can be learned statistically by grammar induction. We then show that covering the most frequent grammar rules via our language parameters has a strong impact on the parsing accuracy in 12 languages.