The Acquisition of Lexical Knowledge from Combined Machine-Readable Dictionary Sources

The Acquisition of Lexical Knowledge from Combined Machine-Readable Dictionary Sources Antonio Sanfilippo* Computer Laboratory, University of Cambridge New Museum Site, Pembroke Street Cambridge CB2 3QG, UK Antonio.Sanfilippo~cl.cam.ac.uk Victor Poznatlski IRIDIA, Universit~ Libre de Bruxelles 50 Avenue F. Roosevelt, CP 194/6 B-1050 Bruxelles, Belgique vicpoz~isl.vub.ac.be Abstract This paper is concerned with the question of how to extract lexical knowledge from Machine- Readable Dictionaries (MRDs) within a lexi- cal database which integrates a lexicon devel- opment environment. Our long term objective is the creation of a large lexical knowledge base using semiautomatic techniques to recover syn- tactic and semantic information from MRDs. In doing so, one finds that reliance on a single MRD source induces inadequacies which could be efficiently redressed through access to com- bined MRD sources. In the general case, the integration of information from distinct MRDs remains a problem hard, perhaps impossible, to solve without the aid of a complete, linguisti- cally motivated database which provides a ref- erence point for comparison. Nevertheless, ad- vances can be made by attempting to correlate dictionaries which are not too dissimilar. In keeping with these observations, we describe a software package for correlating MRDs based on sense merging techniques and show how such a tool can be employed in augmenting a lexical knowledge base built from a conventional MRD with thesaurus information. 1 Introduction Over the last few years, the utilization of machine read- able dictionaries (MRDs) in compiling lexical compo- nents for Natural Language Processing (NLP) systems has awakened the interest of an increasing number of re- searchers. This trend has largely arisen from the recog- nition that access to a large scale Lexical Knowledge Base (LKB) is a sine qua non for real world applica- tions of NLP systems. Computer-aided acquisition of lexical knowledge from MRDs can be made to satisfy this prerequisite in a manner which is both time- and cost- effective. However, to maximize the utility of MRDs in *The research reported in this paper was carried out at the Computer Laboratory (University of Cambridge) as part of an ongoing study on the acquisition of lexical knowledge from machine-readable dictionaries within the ACQUILEX project, ESPRIT BRA 3030. NLP applications, it is necessary to overcome inconsis- tencies, omissions and the occasional errors which are commonly found in MRDs (Atkins el al., 1986; Atkins, 1989; Akkerman, 1989; Boguraev & Briscoe, 1989). This goal can be partly achieved by developing tools which make it possible to correct errors and inconsistencies contained in the information structures automatically derived from the source MRD before these are stored in the LKB or target lexicon (Carroll & Grover, 1989). This technique is nevertheless of little avail in redress- ing inadequacies which arise from lack of information. In this case, manual supply of the missing information would be too time- and labour-intensive to be desirable. Moreover, the information which is missing can be usu- ally obtained from other MRD sources. Consider, for ex- ample, a situation in which we wanted to augment lexical representations available from …

Content truncated to 500 words