tailieunhanh - Báo cáo khoa học: "Trainable Sentence Planning for Complex Information Presentation in Spoken Dialog Systems"

A challenging problem for spoken dialog systems is the design of utterance generation modules that are fast, flexible and general, yet produce high quality output in particular domains. A promising approach is trainable generation, which uses general-purpose linguistic knowledge automatically adapted to the application domain. This paper presents a trainable sentence planner for the MATCH dialog system. | Trainable Sentence Planning for Complex Information Presentation in Spoken Dialog Systems Amanda Stent Stony Brook University Stony Brook NY 11794 . stent@ Rashmi Prasad University of Pennsylvania Philadelphia PA 19104 . rjprasad@ Marilyn Walker University of Sheffield Sheffield S1 4DP . Abstract A challenging problem for spoken dialog systems is the design of utterance generation modules that are fast flexible and general yet produce high quality output in particular domains. A promising approach is trainable generation which uses general-purpose linguistic knowledge automatically adapted to the application domain. This paper presents a trainable sentence planner for the MATCH dialog system. We show that trainable sentence planning can produce output comparable to that of match s template-based generator even for quite complex information presentations. 1 Introduction One very challenging problem for spoken dialog systems is the design of the utterance generation module. This challenge arises partly from the need for the generator to adapt to many features of the dialog domain user population and dialog context. There are three possible approaches to generating system utterances. The first is templatebased generation used in most dialog systems today. Template-based generation enables a programmer without linguistic training to program a generator that can efficiently produce high quality output specific to different dialog situations. Its drawbacks include the need to 1 create templates anew by hand for each application 2 design and maintain a set of templates that work well together in many dialog contexts and 3 repeatedly encode linguistic constraints such as subject-verb agreement. The second approach is natural language generation NLG which divides generation into 1 text or content planning 2 sentence planning and 3 surface realization. NLG promises portability across domains and dialog .

crossorigin="anonymous">
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.