Heshaam Feili’s research while affiliated with Sharif University of Technology and other places

Grammar induction, also known as grammar inference, is one of the most important research areas in the domain of natural language processing. Availability of large corpora has encouraged many researchers to use statistical methods for grammar induction. This problem can be divided into three different categories of supervised, semi-supervised, and unsupervised, based on type of the required data set for the training phase. Most current inductive methods are supervised, which need a bracketed data set for their training phase; but the lack of this kind of data set in many languages, encouraged us to focus on unsupervised approaches. Here, we introduce a novel approach, which we call history-based inside-outside (HIO), for unsupervised grammar inference, by using part-of-speech tag sequences as the only source of lexical information. HIO is an extension of the inside-outside algorithm enriched by using some notions of history based approaches. Our experiments on English and Persian languages show that by adding some conditions to the rule assumptions of the induced grammar, one can achieve acceptable improvement in the quality of the output grammar.

Grammar induction is one of the most important research areas of the natural language processing. The lack of a large Treebank, which is required in supervised grammar induction, in some natural languages such as Persian encouraged us to focus on unsupervised methods. We have found the Inside-Outside algorithm, introduced by Lari and Young, as a suitable platform to work on, and augmented IO with a history notion. The result is an improved unsupervised grammar induction method called History-based IO (HIO). Applying HIO to two very divergent natural languages (i.e., English and Persian) indicates that inducing more conditioned grammars improves the quality of the resultant grammar. Besides, our experiments on ATIS and WSJ show that HIO outperforms most current unsupervised grammar induction methods.

Increasing the domain of locality by using Tree Adjoining Grammars (TAG) caused some applications, such as machine translation, to employ it for the disambigu ation process. Successful experiments of employing TAG in French-English and Korean-English machine translation encouraged us to use it for another language pairs with very divergent properti es, Persian and English. Using Synchronous TAG (S-TAG) for this pair of languages can benefit from syntactic and semantic f eatures for transferring the source into the target language. H ere, we report our experiments in translating English into Persian. Al so, we present a model for lexical selection disambiguation based on the decision trees notion. An automatic learning method of the r equired decision trees from a sample data set is introduced , too.

Increasing the domain of locality by using tree-adjoining-grammars (TAG) caused some applications, such as machine translation, to employ it for disambiguation process (2). Successful experiments of applying TAG grammar to French-English and Korean-English machine translation encouraged us to use it for another language pairs with very divergent properties, Persian and English (2, 10). Using Synchronous TAG (S-TAG) for this pair of languages can benefit from syntactic and semantic features for transferring the source language to a target language. S-TAG, is a pair of TAGs for source-target languages with some correspondence between the nodes of elementary trees of TAGs. Here, we report our experiments in the translation from English into Persian. We discuss problems that are specific to Persian and propose appropriate solutions.