A Status Report on the LRC Machine

A STATUS REPORT ON THE LRC MACHINE Jonathan Slocum Siemens Corporation Boca Eaton, FL 3343 ABSTRACT This paper discusses the linguistic and computational techniques employed in the current version of Machine Translation system being developed at the Linguistics Research Center of the University of Texas, under contract to Siemens AG in Munich, West Germany. We pay particular attention to the reasons for our choice of certain techniques over other candidates, based on both objective and subjective criteria. We then report the system's status vis-a-vis its readiness for application in a production environment, as a means of justifying our claims regarding the practical utility of the methods we espouse. I INTRODUCTION The LRC MT system is one of very few large-scale applications of modern computational linguistics techniques [Lehmann, 1981]. Although the LRC MT system is nearing the status of a production system (a version should be delivered to the project sponsor about the time this conference takes place), it is not at all static; rather, it is an evolving collection of techniques which are continually tested through application to moderately large technical manuals ranging from 50 to 200 pages in length. Thus, our "applied" system remains a research vehicle that serves as an excellent testbed for proposed new procedures. In general, the criteria for our choice of linguistic and computational techniques are three: effectiveness, convenience of use, and efficiency. These criteria are applied in a context where the production of an MT system to be operational in the near-term future is of critical concern. Candidate techniques which do not admit near-term, large-scale application thus suffer an over- whelmins disadvantage. The questions confronting us are, then, twofold: (I) which techniques admit such application; and (2) which of these best satisfy our three general criteria? The first question is usually answered through an evaluation of the likely difficulties and requirements for implementation; the second, through empirical results in the course of experiments. Our evaluation of the LRC ~E system's current status will be based on three points! (a) the system's provision of all the tools necessary for users to effect the complete translation process (including text processing, editing, terminology meinten~ok-up, etc.); (b) quantitae., throughput on a particul. (c) qualitative PerformS'known about overall performliveness (i.e., the number c o be] supported by a single " • , m, cheer [expected] cnrougnp any other personnel necessar-to-day operation of the sySted ] overall costs of translat the norm experienced in human-fine I numbers" will not be a of the conference. but the ninary experiments by our sponthus some reasonable projecti, ~UES EMPLOYED Our ~een "linguistic ceohniqu%ional techniques" (dlscussqection) is somewhat artificihalidity in a broad sense, aSfrom an overview of the point s section we present the reas of the following linguistia phrase-structure grammar; ures; (c) semantic features;erpretations; (e) transformecific rules; (f) a transfer:Cached procedures to effect tt 166 A. Phras, In ,e employ a phrase- structur~Y sufficient lexical controls ~ lexical-funccional grammar all our linguistic decision most controversial, and cons the most attention. Generall are two …

Content truncated to 500 words