Experiments in parallel-text based grammar induction

Experiments in Parallel-Text Based Grammar Induction Jonas Kuhn Department of Linguistics The University of Texas at Austin Austin, TX 78712 jonak@mail.utexas.edu Abstract This paper discusses the use of statistical word alignment over multiple parallel texts for the identi- fication of string spans that cannot be constituents in one of the languages. This information is ex- ploited in monolingual PCFG grammar induction for that language, within an augmented version of the inside-outside algorithm. Besides the aligned corpus, no other resources are required. We discuss an implemented system and present experimental results with an evaluation against the Penn Tree- bank. 1 Introduction There have been a number of recent studies exploit- ing parallel corpora in bootstrapping of monolin- gual analysis tools. In the “information projection” approach (e.g., (Yarowsky and Ngai, 2001)), statis- tical word alignment is applied to a parallel corpus of English and some other language � for which no tagger/morphological analyzer/chunker etc. (hence- forth simply: analysis tool) exists. A high-quality analysis tool is applied to the English text, and the statistical word alignment is used to project a (noisy) target annotation to the � version of the text. Robust learning techniques are then applied to boot- strap an analysis tool for � , using the annotations projected with high confidence as the initial train- ing data. (Confidence of both the English analysis tool and the statistical word alignment is taken into account.) The results that have been achieved by this method are very encouraging. Will the information projection approach also work for less shallow analysis tools, in particular full syntactic parsers? An obvious issue is that one does not expect the phrase structure representa- tion of English (as produced by state-of-the-art tree- bank parsers) to carry over to less configurational languages. Therefore, (Hwa et al., 2002) extract a more language-independent dependency structure from the English parse as the basis for projection to Chinese. From the resulting (noisy) dependency treebank, a dependency parser is trained using the techniques of (Collins, 1999). (Hwa et al., 2002) re- port that the noise in the projected treebank is still a major challenge, suggesting that a future research focus should be on the filtering of (parts of) unre- liable trees and statistical word alignment models sensitive to the syntactic projection framework. Our hypothesis is that the quality of the result- ing parser/grammar for language � can be signifi- cantly improved if the training method for the parser is changed to accomodate for training data which are in part unreliable. The experiments we report in this paper focus on a specific part of the prob- lem: we replace standard treebank training with an Expectation-Maximization (EM) algorithm for PCFGs, augmented by weighting factors for the re- liability of training data, following the approach of (Nigam et al., 2000), who apply it for EM train- ing of a text classifier. The factors are only sen- sitive to the constituent/distituent (C/D) status of each span of the string in � (cp. (Klein and Man- ning, 2002)). The C/D status …

Content truncated to 500 words