Louise Guthrie

Lexical disambiguation using simulated annealing

The resolution of lexical ambiguity is important for most natural language processing tasks, and a range of computational techniques have been proposed for its solution. None of these has yet proven effective on a large scale. In this paper, we describe a method for lexical disambiguation of text using the definitions in a machine-readable dictionary together with the technique of simulated annealing. The method operates on complete sentences and attempts to select the optimal combinations of word senses for all the words in the sentence simultaneously. The words in the sentences may be any of the 28,000 headwords in Longmans Dictionary of Contemporary English (LDOCE) and are disambiguated relative to the senses given in LDOCE. Our initial results on a sample set of 50 sentences are comparable to those of other researchers, and the fully automatic method requires no hand-coding of lexical entries, or hand-tagging of text.

Is there content in empty heads

We describe a technique for automatically constructing a taxonomy of word senses from a machine readable dictionary. Previous taxonomies developed from dictionaries have two properties in common. First, they are based on a somewhat loosely defined notion of the IS-A relation. Second, they require human intervention to identify the sense of the genus term being used. We believe that for taxonomies of this type to serve a useful role in subsequent natural language processing tasks, the taxonomy must be based on a consistent use of the IS-A relation which allows inheritance and transitivity. We show that hierarchies of this type can be automatically constructed, by using the semantic category codes and the subject codes of the Longman Dictionary of Contemporary English (LDOCE) to disambiguate the genus terms in noun definitions. In addition, we discuss how certain genus terms give rise to other semantic relations between definitions.

Genus disambiguation: a study in weighted preference

The automatic construction of an IS_A taxonomy of noun senses from a machine readable dictionary (MRD) has long been sought, but achieved with only limited success. The task requires the solution to two problems: 1) To define an algorithm to automatically identify the genus or hypernym of a noun definition, and 2) to define an algorithm for lexical disambiguation of the genus term. In the last few years, effective methods for solving the first problem have been developed, but the problem of creating an algorithm for lexical disambiguation of the genus terms is one that has proven to be very difficult. In COLING 90 we described our initial work on the automatic creation of a taxonomy of noun senses from Longmans Dictionary of Contemporary English (LDOCE). The algorithm for lexical disambiguation of the genus term was accurate about 80% of the time and made use of the semantic categories, the subject area markings and the frequency of use information in LDOCE. In this paper we report a series of experiments which weight the three factors in various ways, and describe our improvements to the algorithm (to about 90% accuracy).

Document classification by machine: theory and practice

In this note, we present results concerning the theory and practice of determining for a given document which of several categories it best fits. We describe a mathematical model of classification schemes and the one scheme which can be proved optimal among all those based on word frequencies. Finally, we report the results of an experiment which illustrates the efficacy of this classification method.

Automatically Creating Lexical Entries for ULTRA, a Multilingual MT System*

In this paper, we describe both a multi-lingual, interlingual MT system (ULTRA) and a method of extracting lexical entries for it automatically from an existing machine-readable dictionary (LDOCE). We believe the latter is original and the former, although not the first interlingual MT System by any means, may be first that is symmetrically multi-lingual. It translates between English, German, Chinese, Japanese and Spanish and has vocabularies in each language based on about 10,000 word senses.

The automatic creation of lexical entries for a multilingual MT system

In this paper, we describe a method of extracting information from an on-line resource for the construction of lexical entries for a multi-lingual, interlingual MT system (ULTRA). We have been able to automatically generate lexical entries for interlingual concepts corresponding to nouns, verbs, adjectives and adverbs. Although several features of these entries continue to be supplied manually we have greatly decreased the time required to generate each entry and see this as a promising method for the creation of large-scale lexicons.

Parsing in parallel

The paper is a description of a parallel model for natural language parsing, and a design for its implementation on the Hypercube multiprocessor. The parallel model is based on the Semantic Definite Clause Grammar formation and integrates syntax and semantics through the communication of processes. The main processess, of which there are six, contain either purely syntactic or purely semantic information, giving the advantage of simple, transparent algorithms dedicated to only one aspect of parsing. Communication between processes is used to impose semantic constraints on the syntactic processes.

CRL/BRANDEIS: THE DIDEROT SYSTEM

Diderot is an information extraction system built at CRL and Brandeis University over the past two years. It was produced as part of our efforts in the Tipster project. The same overall system architecture has been used for English and Japanese and for the micro-electronics and joint venture domains.

CRL/NMSU and Brandeis: description of the MucBruce system as used for MUC-4

Through their involvement in the Tipster project the Computing Research Laboratory at New Mexico State University and the Computer Science Department at Brandeis University are developing a method for identifying articles of interest and extracting and storing specific kinds of information from large volumes of Japanese and English texts. We intend that the method be general and extensible. The techniques involved are not explicitly tied to these two languages nor to a particular subject area. Development for Tipster has been going on since September, 1992.

CRL/Brandeis: description of the Diderot system as used for MUC-5

This report describes the major developments over the last six months in completing the Diderot information extraction system for the MUC-5 evaluation.Diderot is an information extraction system built at CRL and Brandeis University over the past two years. It was produced as part of our efforts in the Tipster project. The same overall system architecture has been used for English and Japanese and for the micro-electronics and joint venture domains.The past history of the system is discussed and the operation of its major components described. A summary of scores at the 24 month workshop is given and the performance of the system on the texts selected for the system walkthrough is discussed.