Rule-based Acquisition and Maintenance of Lexical and Semantic Knowledge

Rule-based Acquisition and Maintenance of Lexical and Semantic Knowledge * Donna M. Gates and Peter Shell Internet: dmg@cmu.edu, pshell@cmu.edu Center for Machine Translation Carnegie Mellon University 5000 Forbes Avenue Pittsburgh, PA 15213 U.S.A. Abstract The lexicons for Knowledge-Based Machine Translation systems require knowledge in- tensive morphological, syntactic and se- mantic information. This information is of- ten used in different ways and usually for- matted for a specific NLP system. This tends to make both the acquisition and maintenance of lexical databases cumber- some, inefficient and error-prone. In order to solve these problems, we have developed a program called COOL which automates the acquisition and maintenance processes and allows us to standardize and central- ize the databases. This system is currently being used in the ESTRATO machine trans- lation project at the Center for Machine Translation. 1 Introduction In this paper, we describe a fully-implemented rule- based system for the semi-automatic acquisition and maintenance of lexical and semantic knowledge in a knowledge-based machine translation system. This rule-based system is called COOL: Creator Of ontologies and Lexicons. COOL can create and up- date various lexical and semantic knowledge sources for different NLP modules. COOL is a working system that was developed for ESTRATO (EScuela de TRAductores de TOledo), a joint project of the Center for Machine Translation at CMU and Union Electrica Fenosa, an electric util- ity company in Madrid, Spain. ESTRATO is a system *This project was funded by Union Electrica Fenosa, Madrid, Spain. for translating Spanish to English in a restricted do- main with controlled input. ESTRATO consists of sev- eral modules from the KANT MT system [Mitamura et al., 1991] as well as morphological analysis and phrasal recognition modules and the TWS authoring environment[Nirenburg et ai., 1992]. As shown in figure 1, every ESTRATO run-time module uses a different lexical or semantic knowledge source, which differs in content as well as format. The knowledge contained in these modules overlaps. We needed to coordinate and maintain these know- ledge sources in a robust and efficient way. Further- more, the lexical information needed by the trans- lator is initially acquired by people ("editors") who are neither linguists nor domain experts. This lex- ical information is kept in lexical feature files. 1 We needed a way to convert these lexical feature files into forms which could be used by the run-time modules of ESTRATO. Our solution is to maintain a centralized lexical and semantic frame database, and to use COOL to help us acquire this database by converting the ini~ tial feature files created by the human editors. The lexical and semantic knowledge sources needed by the run-time translator are then automatically gener- ated and maintained by COOL. Two subsystems per- form these tasks: ACQUISITION-COOL (A-COOL) and MAINTENANCE-COOL (M-COOL). A-COOL produces the central lexical and template semantic databases from the initial lexical feature files, which the linguist and domain expert can then modify. M-COOL goes beyond simple acquisition of lexical information. It automatically generates efficient run-time versions of the lexical and semantic …

Content truncated to 500 words