Encoding Frequency Information in Lexicalized Grammars

This document describes a sizable grammar of English written in the TAG formalism and implemented for use with the XTAG system. This report and the grammar described herein supersedes the TAG grammar described in an earlier 1995 XTAG technical report. The English grammar described in this report is based on the TAG formalism which has been extended to include lexicalization, and unification-based feature structures. The range of syntactic phenomena that can be handled is larg...

This paper explores the kinds of probabilistic relations that are important in syntactic disambiguation. It proposes that two widely used kinds of relations, lexical dependencies and structural relations, have complementary disambiguation capabilities. It presents a new model based on structural relations, the Tree-gram model, and reports experiments showing that structural relations should benefit from enrichment by lexical dependencies.

Supertagging is an approach originally developed by Bangalore and Joshi (1999) to improve the parsing efficiency. In the beginning, the scholars used small training datasets and somewhat na\"ive smoothing techniques to learn the probability distributions of supertags. Since its inception, the applicability of Supertags has been explored for TAG (tree-adjoining grammar) formalism as well as other related yet, different formalisms such as CCG. This article will try to summarize...

This thesis presents a computational theory of unsupervised language acquisition, precisely defining procedures for learning language from ordinary spoken or written utterances, with no explicit help from a teacher. The theory is based heavily on concepts borrowed from machine learning and statistical estimation. In particular, learning takes place by fitting a stochastic, generative model of language to the evidence. Much of the thesis is devoted to explaining conditions tha...

This paper uses the Minimum Description Length paradigm to model the complexity of CxGs (operationalized as the encoding size of a grammar) alongside their descriptive adequacy (operationalized as the encoding size of a corpus given a grammar). These two quantities are combined to measure the quality of potential CxGs against unannotated corpora, supporting discovery-device CxGs for English, Spanish, French, German, and Italian. The results show (i) that these grammars provid...

This thesis presents a broad-coverage probabilistic top-down parser, and its application to the problem of language modeling for speech recognition. The parser builds fully connected derivations incrementally, in a single pass from left-to-right across the string. We argue that the parsing approach that we have adopted is well-motivated from a psycholinguistic perspective, as a model that captures probabilistic dependencies between lexical items, as part of the process of bui...

Eric Brill has recently proposed a simple and powerful corpus-based language modeling approach that can be applied to various tasks including part-of-speech tagging and building phrase structure trees. The method learns a series of symbolic transformational rules, which can then be applied in sequence to a test corpus to produce predictions. The learning process only requires counting matches for a given set of rule templates, allowing the method to survey a very large space ...

Automatic language processing tools typically assign to terms so-called weights corresponding to the contribution of terms to information content. Traditionally, term weights are computed from lexical statistics, e.g., term frequencies. We propose a new type of term weight that is computed from part of speech (POS) n-gram statistics. The proposed POS-based term weight represents how informative a term is in general, based on the POS contexts in which it generally occurs in la...

In this thesis, we investigate three problems involving the probabilistic modeling of language: smoothing n-gram models, statistical grammar induction, and bilingual sentence alignment. These three problems employ models at three different levels of language; they involve word-based, constituent-based, and sentence-based models, respectively. We describe techniques for improving the modeling of language at each of these levels, and surpass the performance of existing algorith...

In natural language processing (NLP), the likelihood ratios (LRs) of N-grams are often estimated from the frequency information. However, a corpus contains only a fraction of the possible N-grams, and most of them occur infrequently. Hence, we desire an LR estimator for low- and zero-frequency N-grams. One way to achieve this is to decompose the N-grams into discrete values, such as letters and words, and take the product of the LRs for the values. However, because this metho...