A Bilingual VOYAGER System

Y. Glass, A • Bilingual VOYAGER System 1 D. Goodine, M. Phillips, S. Sakai 2, S. Seneff, Spoken Language Systems Group• Laboratory for Computer Science Massachusetts Institute of Technology Cambridge, Massachusetts 02139 and V. Zue 3 ABSTRACT This paper describes our initial efforts at porting the VOY- AGER spoken language system to Japanese. In the process we have reorganized the structure of the system so that lan- guage dependent information is separated from the core en- gine as much as possible. For example, this information is encoded in tabular or rule-based form for the natural lan- guage understanding and generation components. The inter- nal system manager, discourse and dialogue component, and database are all maintained in language transparent form. Once the generation component was ported, data were col- lected from 40 native speakers of Japanese using a wizard collection paradigm. A portion of these data was used to train the natural language and segment-based speech recog- nition components. The system obtained an overall under- standing accuracy of 52~0 on the test data, which is similar to our earlier reported results for English [i]. INTRODUCTION In the fall of 1989, our group first demonstrated VOY- AGER, a system that can engage in verbal dialogues with users about a geographical region within Cambridge, Mas- sachusetts [2]. The system can provide users with infor- mation about distances, travel times, or directions be- tween objects located within this area (e.g., restaurants, hotels, post offices, subway stops), as well as informa- tion such as addresses or telephone numbers of the ob- jects themselves. While VOYAGER is constrained both in its capabilities and domain of knowledge, it contains all the essential components of a spoken-language sys- tem, including discourse maintenance and language gen- eration. The VOYAGER application provided us with our first experience with the development of spoken language systems, helped us understand the issues related to this endeavor, and provided a framework for our subsequent system development efforts [3, 4]. 1This research was supported by DARPA under Contract N00014-89-J-1332, monitored through the Office of Naval Research. 2Currently a visiting scientist from NEC Corp, Kawasaki, Japan. 3The authors are listed in alphabetical order. 49 Over the past few years, we have become increas- ingly interested in developing multilingual spoken lan- guage systems. There are several ongoing international spoken language translation projects whose goal is to en- able humans to communicate with each other in their imtive tongues [5, 6]. Our objective, however, is some- what different. Specifically, we are interested in devel- oping multilingual human-computer interfaces, such that the information stored in the database can be accessed and received in multiple spoken languages. We believe that there is great utility in having such systems, since information is fast becoming globally accessible. Fur- thermore, we suspect that this type of multilingual sys- tem may be easier to develop than speech translation systems, since the system only needs to anticipate the diversity of one side of the conversation, i.e., the human side. During the past year, we have …

Content truncated to 500 words