Results 11 - 20
of
25
Learning to Map Sentences to Logical Form
, 2009
"... One of the classical goals of research in artificial intelligence is to construct systems that automatically recover the meaning of natural language text. Machine learning methods hold significant potential for addressing many of the challenges involved with these systems. This thesis presents new t ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
One of the classical goals of research in artificial intelligence is to construct systems that automatically recover the meaning of natural language text. Machine learning methods hold significant potential for addressing many of the challenges involved with these systems. This thesis presents new techniques for learning to map sentences to logical form — lambda-calculus representations of their meanings. We first describe an approach to the context-independent learning problem, where sentences are analyzed in isolation. We describe a learning algorithm that takes as input a training set of sentences labeled with expressions in the lambda calculus. The algorithm induces a Combinatory Categorial Grammar (CCG) for the problem, along with a log-linear model that represents a distribution over syntactic and semantic analyses conditioned on the input sentence. Next, we present an extension that addresses challenges that arise when learning to analyze spontaneous, unedited natural language input, as is commonly seen in natural language interface applications. A key idea is to introduce non-standard
Unsupervised syntax learning with categorial grammars using inference rules
- In Proc. of the 18th
, 2009
"... We propose a learning method with categorial grammars using inference rules. The proposed learning method has been tested on an artificial language fragment that contains both ambiguity and recursion. We demonstrate that our learner has successfully converged to the target grammar using a relatively ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
We propose a learning method with categorial grammars using inference rules. The proposed learning method has been tested on an artificial language fragment that contains both ambiguity and recursion. We demonstrate that our learner has successfully converged to the target grammar using a relatively small set of initial assumptions. We also show that our method is successful at one of the celebrated problems of language acquisition literature: learning the English auxiliary order. 1.
The Automatic Acquisition of Knowledge about Discourse Connectives
, 2005
"... This thesis considers the automatic acquisition of knowledge about discourse connectives. It focuses in particular on their semantic properties, and on the relationships that hold between them. There is a considerable body of theoretical and empirical work on discourse connec-tives. For example, Kno ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
This thesis considers the automatic acquisition of knowledge about discourse connectives. It focuses in particular on their semantic properties, and on the relationships that hold between them. There is a considerable body of theoretical and empirical work on discourse connec-tives. For example, Knott (1996) motivates a taxonomy of discourse connectives based on relationships between them, such as HYPONYMY and EXCLUSIVE, which are defined in terms of substitution tests. Such work requires either great theoretical insight or manual analysis of large quantities of data. As a result, to date no manual classification of English discourse con-nectives has achieved complete coverage. For example, Knott gives relationships between only about 18 % of pairs obtained from a list of 350 discourse connectives. This thesis explores the possibility of classifying discourse connectives automatically, based on their distributions in texts. This thesis demonstrates that state-of-the-art techniques in lexical acquisition can successfully be applied to acquiring information about discourse connectives. Central to this thesis is the hypothesis that distributional similarity correlates positively with semantic similarity. Support for this hypothesis has previously been found for word classes
Plans and the Computational Structure of Language
"... Not only speech, but all skilled acts seem to involve the same problems of serial ordering, even down to the temporal coordination of muscular contractions in such a movement as reaching and grasping. Analysis of the nervous mechanisms underlying order in the more primitive acts may contribute ultim ..."
Abstract
- Add to MetaCart
Not only speech, but all skilled acts seem to involve the same problems of serial ordering, even down to the temporal coordination of muscular contractions in such a movement as reaching and grasping. Analysis of the nervous mechanisms underlying order in the more primitive acts may contribute ultimately to the solution of even the physiology of logic.
Theory. The Universal Grammar is implemented
"... The purpose of this work is to investigate the process of grammatical acquisition from data. We are using a computational learning systern that is composed of a Universal Grammar with associated parameters, and a learning algorithm, ..."
Abstract
- Add to MetaCart
(Show Context)
The purpose of this work is to investigate the process of grammatical acquisition from data. We are using a computational learning systern that is composed of a Universal Grammar with associated parameters, and a learning algorithm,
PhD Proposal – The Lexicon in Combinatory Categorial Grammar: An Explanatory Theory of Verbal Categories in Natural Languages
, 2002
"... The aim of this project is to elaborate a theory of natural language lexicons for Combinatory Categorial Grammar (CCG), a mildly contextsensitive, polynomially time-parsable variant of categorial grammar. This theory will have both a descriptive aspect, exploring the use of appropriate formal machin ..."
Abstract
- Add to MetaCart
The aim of this project is to elaborate a theory of natural language lexicons for Combinatory Categorial Grammar (CCG), a mildly contextsensitive, polynomially time-parsable variant of categorial grammar. This theory will have both a descriptive aspect, exploring the use of appropriate formal machinery for expressing lexical generalisations, and an explanatory aspect, accounting for observed patterns of language variation, acquisition and change. Where appropriate insights will be incorporated from other grammar formalisms such as unification-based grammar and Principles and Parameters Theory. Particular focus will be placed on clausal word order variation among the Germanic languages, which have been both the subject of a substantial Principles and Parameters literature, as well as of much speculative work in extended categorial grammar. A common theme of this project will be to explore the option of replacing analyses of word order phenomena involving powerful permutative combinatory operations, with analyses rooted in the lexicon. 1
Abstract Minimal Recursion Semantics
"... Minimal recursion semantics (MRS) is a framework for computational semantics that is suitable for parsing and ..."
Abstract
- Add to MetaCart
Minimal recursion semantics (MRS) is a framework for computational semantics that is suitable for parsing and
Contents
, 2005
"... 2.1 Categories and the lexicon.................................. 7 2.2 AB categorial grammar.................................... 8 ..."
Abstract
- Add to MetaCart
2.1 Categories and the lexicon.................................. 7 2.2 AB categorial grammar.................................... 8
Learning to Distinguish PP Arguments from Adjuncts
"... Words di#er in the subcategorisation frames in which they occur, and there is a strong correlation between the semantic arguments of a given word and its subcategorisation frame, so that all its arguments should be included in its subcategorisation frame. One problem is posed by the ambiguity betwee ..."
Abstract
- Add to MetaCart
Words di#er in the subcategorisation frames in which they occur, and there is a strong correlation between the semantic arguments of a given word and its subcategorisation frame, so that all its arguments should be included in its subcategorisation frame. One problem is posed by the ambiguity between locative prepositional phrases as arguments of a verb or adjuncts. As the semantics for the verb is the same in both cases, it is di#cult to di#erentiate them, and to learn the appropriate subcategorisation frame. We propose an approach that uses semantically motivated preposition selection and frequency information to determine if a locative PP is an argument or an adjunct. In order to test this approach, we perform an experiment using a computational learning system that receives as input utterances annotated with logical forms. The results obtained indicate that the learner successfully distinguishes between arguments (obligatory and optional) and adjuncts.
