tailieunhanh - Báo cáo khoa học: "Unsupervised Multilingual Grammar Induction"

We investigate the task of unsupervised constituency parsing from bilingual parallel corpora. Our goal is to use bilingual cues to learn improved parsing models for each language and to evaluate these models on held-out monolingual test data. We formulate a generative Bayesian model which seeks to explain the observed parallel data through a combination of bilingual and monolingual parameters. To this end, we adapt a formalism known as unordered tree alignment to our probabilistic setting. | Unsupervised Multilingual Grammar Induction Benjamin Snyder Tahira Naseem and Regina Barzilay Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology bsnyder tahira regina @ Abstract We investigate the task of unsupervised constituency parsing from bilingual parallel corpora. Our goal is to use bilingual cues to learn improved parsing models for each language and to evaluate these models on held-out monolingual test data. We formulate a generative Bayesian model which seeks to explain the observed parallel data through a combination of bilingual and monolingual parameters. To this end we adapt a formalism known as unordered tree alignment to our probabilistic setting. Using this formalism our model loosely binds parallel trees while allowing language-specific syntactic structure. We perform inference under this model using Markov Chain Monte Carlo and dynamic programming. Applying this model to three parallel corpora Korean-English Urdu-English and Chinese-English we find substantial performance gains over the CCM model a strong monolingual baseline. On average across a variety of testing scenarios our model achieves an absolute gain in F-measure. 1 1 Introduction In this paper we investigate the task of unsupervised constituency parsing when bilingual parallel text is available. Our goal is to improve parsing performance on monolingual test data for each language by using unsupervised bilingual cues at training time. Multilingual learning has been successful for other linguistic induction tasks such as lexicon acquisition morphological segmentation and part-of-speech tagging Genzel 2005 Snyder and Barzilay 2008 Snyder et al. 2008 Snyder Code and the outputs of our experiments are available at http rbg code multilingjnduction. et al. 2009 . We focus here on the unsupervised induction of unlabeled constituency brackets. This task has been extensively studied in a monolingual setting and has