tailieunhanh - Báo cáo khoa học: "A speech interface for open-domain question-answering"

Speech interfaces to question-answering systems offer significant potential for finding information with phones and mobile networked devices. We describe a demonstration of spoken question answering using a commercial dictation engine whose language models we have customized to questions, a Web-based textprediction interface allowing quick correction of errors, and an open-domain question-answering system, AnswerBus, which is freely available on the Web. We describe a small evaluation of the effect of recognition errors on the precision of the answers returned and make some concrete recommendations for modifying a question-answering system for improving robustness to spoken input. . | A speech interface for open-domain question-answering Edward Schofield ftw. Telecommunications Research Center Vienna Austria Department of Computing Imperial College London . schofield@ Zhiping Zheng Dept. of Computational Linguistics Saarland University Saarbrucken Germany zheng@ Abstract Speech interfaces to question-answering systems offer significant potential for finding information with phones and mobile networked devices. We describe a demonstration of spoken question answering using a commercial dictation engine whose language models we have customized to questions a Web-based textprediction interface allowing quick correction of errors and an open-domain question-answering system AnswerBus which is freely available on the Web. We describe a small evaluation of the effect of recognition errors on the precision of the answers returned and make some concrete recommendations for modifying a question-answering system for improving robustness to spoken input. 1 Introduction This paper demonstrates a multimodal interface for asking questions and retrieving a set of likely answers. Such an interface is particularly appropriate for mobile networked devices with screens that are too small to display general Web pages and documents. Palm and Pocket PC devices whose screens commonly display 10-15 lines are candidates. Schofield and Kubin 2002 argue that for such devices question-answering is more appropriate than traditional document retrieval. But until recently no method has existed for inputting questions in a reasonable amount of time. The study of Schofield 2003 concludes that questions tend to have a limited lexical structure that can be exploited for accurate speech recognition or text prediction. In this demonstration we test whether this result can endow a real spoken question answering system with acceptable precision. 2 Related research Kupiec and others 1994 at Xerox labs built one of the earliest spoken information retrieval .

TỪ KHÓA LIÊN QUAN
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.