We present a knowledge and context-based system for parsing and translating natural language and evaluate it on sentences from the Wall Street Journal. Applying machine learning techniques, the system uses parse action examples acquired under supervision to generate a deterministic shift-reduce parser in the form of a decision structure. It relies heavily on context, as encoded in features which describe the morphological, syntactic, semantic and other aspects of a given parse state.

Automating the construction of semantic grammars is a difficult and interesting problem for machine learning. This paper shows how the semantic-grammar acquisition problem can be viewed as the learning of search-control heuristics in a logic program. Appropriate control rules are learned using a new first-order induction algorithm that automatically invents useful syntactic and semantic categories. Empirical results show that the learned parsers generalize well to novel sentences and out-perform previous approaches based on connectionist techniques. Introduction Designing computer systems to "understand" natural language input is a difficult task. The laboriously hand-crafted computational grammars supporting natural language applications are often inefficient, incomplete and ambiguous. The difficulty in constructing adequate grammars is an example of the "knowledge acquisition bottleneck" which has motivated much research in machine learning. While numerous researchers have studied ...

Abstract not found

Current approaches to computational lexicology in language technology are knowledge-based (competence-oriented) and try to abstract away from specific formalisms, domains, and applications. This results in severe complexity, acquisition and reusability bottlenecks. As an alternative, we propose a particular performance-oriented approach to Natural Language Processing based on automatic memory-based learning of linguistic (lexical) tasks. The consequences of the approach for computational lexicology are discussed, and the application of the approach on a number of lexical acquisition and disambiguation tasks in phonology, morphology and syntax is described.

This paper addresses the issue of "algorithm vs. representation" for case-based learning of linguistic knowledge. We first present empirical evidence that the success of case-based learning methods for natural language processing tasks depends to a large degree on the feature set used to describe the training instances. Next, we present a technique for automating feature set selection for case-based learning of linguistic knowledge. Given as input a baseline case representation, the method modifies the representation in response to a number of predefined linguistic biases by adding, deleting, and weighting features appropriately. We apply the linguistic bias approach to feature set selection to the problem of relative pronoun disambiguation and show that the casebased learning agorithm improves as relevant biases are incorporated into the underlying instance representation. Finally, we argue that the linguistic bias approach to feature set selection offers new possibilities for case-based learning of natural language: it simplifies the process of instance representation design and, in theory, obviates the need for separate instance representations for each linguistic knowledge acquisition task. More importantly, the approach offers a mechanism for explicitly combining the frequency information available from corpus-based techniques with linguistic bias information employed in traditional linguistic and knowledge-based approaches to natural language processing.

This paper reviews our recent work on applying inductive logic programming to the construction of natural language processing systems. We have developed a system, Chill, that learns a parser from a training corpus of parsed sentences by inducing heuristics that control an initial overly-general shift-reduce parser. Chill learns syntactic parsers as well as ones that translate English database queries directly into executable logical form. The ATIS corpus of airline information queries was used to test the acquisition of syntactic parsers, and Chill performed competitively with recent statistical methods. English queries to a small database on U.S. geography were used to test the acquisition of a complete natural language interface, and the parser that Chill acquired was more accurate than an existing hand-coded system. The paper also includes a discussion of several issues this work has raised regarding the capabilities and testing of ILP systems as well as a summary of our current research directions.

For most natural language processing tasks, a parser that maps sentences into a semantic representation is significantly more useful than a grammar or automata that simply recognizes syntactically wellformed strings. This paper reviews our work on using inductive logic programming methods to learn deterministic shift-reduce parsers that translate natural language into a semantic representation. We focus on the task of mapping database queries directly into executable logical form. An overview of the system is presented followed by recent experimental results on corpora of Spanish geography queries and English jobsearch queries. Introduction Language learning is frequently interpreted as acquiring a recognizer, a procedure that returns "yes" or "no" to the question: "Is this string a syntactically wellformed sentence in the language?". However, a blackbox recognizer is of limited use to a natural language processing system. A simple recognizer may be useful to a limited grammar checke...

Simple Recurrent Networks (SRNs) have been widely used in natural language tasks. SARDSRN extends the SRN by explicitly representing the input sequence in a SARDNET self-organizing map.

ROLE VALUES A Thesis Submitted to the Faculty Purdue University by Christopher M. White In Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy May 2000 - ii - To my loving wife Margit.

Simple Recurrent Networks (SRNs) have been widely used in natural language processing tasks. However, their ability to handle long-term dependencies between sentence constituents is somewhat limited. NARX networks have recently been shown to outperform SRNs by preserving past information in explicit delays from the network's prior output. However, it is unclear how the number of delays should be determined. In this study on a shift-reduce parsing task, we demonstrate that comparable performance can be derived more elegantly by using a SARDNET self-organizing map. The resulting architecture can represent arbitrarily long sequences and is cognitively more plausible. Introduction The subsymbolic approach (i.e. neural networks with distributed representations) to processing language is attractive for several reasons. First, it is inherently robust: the distributed representations display graceful degradation of performance in the presence of noise, damage, and incomplete or conflicting in...