Augmented Role Filling Capabilities for Semantic Interpretation of Spoken Language

Augmented Role Filling Capabilities for Semantic Interpretation of Spoken Language Lewis Norton, Marcia Linebarger, Deborah Dahl, and Nghi Nguyen Unisys Center for Advanced Information Technology Paoli, Pennsylvania 19301 ABSTRACT This paper describes recent work on the Unisys ATIS Spo- ken Language System, and reports benchmark results on nat- ural language, spoken language, and speech recognition. We describe enhancements to the system's semantic processing for handling non.transparent argument structure and enhance- ments to the system's pragmatic processing of material in art. swers displayed to the user. We found that the system's score on the natural language benchmark test decreased from ~8~o to 36~ without these enhancements. We also report results for three spoken language systems, Unisys natural language cou- pled with MIT-Summit speech recognition, Unisys natural lan- guage coupled wish MIT-Lincoln Labs speech recognition and Unisys natural language coupled with BBN speech recognition. Speech recognition results are reported on the results of the Unisys natural language selecting a candidate from the MIT- Summit N-best (N=16). INTRODUCTION Improving the performance of spoken language systems re- quires addressing issues along several fxonts, including ba- sic improvements in natural language processing and speech recognition as well as issues of integration of these compo- nents in spoken language systems. In this paper we report the results of our recent work in each of these areas. * One major area of work has been in the the semantic and pragmatic components of the Unisys natural language process- ins system. The work in semantics enhances the robustness of semantic processing by allowing parses which do not di- rectly express the argument structure expected by semantics to nevertheless be processed in a rule-governed way. In the area of pragmatics we have extended our techniques for bring- ing material displayed to the user into the dialog context to handle several additional classes of references to material in the display. • This work was supported by DARPA contract N000014-89- C0171, administered by the Office of Naval Research. We are grate- fuI to Victor Zue of MIT, Doug Paul of MIT Lincoln Laboratories and John Mak.houl of BBN for making output from their speech recognition systems available to us. We also wish to thank Tim Finln, Rich Fritzson, Don McKay, Jim Meldlnger, and Jan Pastor of Unisys and Lynette Hirschnmn of MIT for their contributions to this work. In the area of integration of speech and natural language, we report on an experiment with three spoken language systems, coupling the same Unisys natural language system to three different speech recognisers as shown in Figure 1. ~" :.,~:::::::.~::~:::::::~::::::::~,,-::::~,.:: l~.'.-'.;,-',.~i.~~.,.~,.,,...,...,,~,~,.,.i-.,..-,,~:~il :- :+: Ptiq0tY x-: .." Figure 1: Unlsys natural language + multiple speech recognlsers We believe this is a very promising technique for evaluat- ing the components of spoken language systems. Using this technique we can make a very straightforward compe~ison of the performance of the recognizers in a spoken language con- text. Furthermore, this technique also allows us to make a fine-gralned comparision of the interaction between speech and natural language in …

Content truncated to 500 words