Spontaneous Speech Parsing in Travel Information Inquiring and Booking Systems

Grammar-based parsing is a prevalent method for natural language understanding(NLU)and has been introduced into dialogue systems for spoken language processing (SLP).A robust parsing scheme is proposed in this paper to overcome the notorious phenomena,such as garbage,ellipsis,word disordering,fragment ,and ill-form,which frequently occur in splien utterances,Keyword categories are used as terminal symbols,and the definition of grammar is extended by introducing three new rule types,by-passing,up-messing and overcrossing,in addition to the general rules called up-tying in this paper,and the use of semantic items simplifies the semantics extraction.The corresponding parser marionette,which is essentially a partial chart parser,is enhanced to parse the semantic grammar.The robust parsing scheme integrating the above methods has been adopted in an air traveling information service system called EasyFlight,and has achieved a high performance when used for parsing spontaneous speeches.

Spontaneous speech parsing in travel information inquiring and booking systems

Grammar-based parsing is a prevalent method for natural language understanding (NLU) and has been introduced into dialogue systems for spoken language processing (SLP). A robust parsing scheme is proposed in this paper to overcome the notorious phenomena, such as garbage, ellipsis, word disordering, fragment, and ill-form, which frequently occur in spoken utterances. Keyword categories are used as terminal symbols, and the definition of grammar is extended by introducing three new rule types,by-passing, up-messing andovercrossing, in addition to the general rules calledup-tying in this paper, and the use of semantic items simplifies the semantics extraction. The corresponding parsermarionette, which is essentially a partial chart parser, is enhanced to parse the semantic grammar. The robust parsing scheme integrating the above methods has been adopted in an air traveling information service system calledEasyFlight, and has achieved a high performance when use for parsing spontaneous speeches. YAN Pengju was born in 1975. He received his Bachelor’s degree and Doctor’s degree from the Department of Computer Science and Technology, Tsinghua University in 1988 and 2002 respectively. His research interests include natural language understanding, automatic speech recognition, and spoken dialogue systems. He had been a core member of the Center of Speech Technology of the State Key Laboratory of Intelligent Technology and Systems and played an important role in the design of two spoken dialogue systems namedEasyNav andEasyFlight. Now he serves as a researcher in Panasonic Beijing Laboratory, the Matsushita Research & Development (China) CO., Ltd in Beijing. ZHENG Fang is currently an associate professor of Tsinghua University. He is the Director of Center of Speech Technology, State Laboratory of Intelligent Technology and Systems. Dr. Zheng graduated from the Department of Computer Science and Technology of Tsinghua University and received his B.S., M.S. and Ph.D. degrees all from Tsinghua University, in 1990, 1992 and 1997 respectively. Dr. Zheng has been working in the area of speech recognition and understanding at the Department of Compute Science and Technology, Tsinghua University, since 1988. He has published over 100 technical papers on acoustic/language modeling, isoiated/continuous speech recognition, keyword spotting, dictating, language understanding, and so on. Dr. Zheng is now an IEEE member, a member of the Artificial Intelligence and Pattern Recognition Technical Commission of China Computer Federation, and m member of the editorial committee of the Joural of Chinese Information Processing. He serves as a reviewer of several domestic and international journals. He is also the Co-Chair of the Program Committee of the 2000 International Symposium on Chinese Spoken Language Processing (ISCLP’2000) and a member of Technical Committee of ’2000 International Conference on Spoken Language Processing (ICSLP’2000). SUN Hui is a Ph.D. candidate of Center of Speech Technology, State Laboratory of Intelligent Technology and Systems of Tsinghua University. She received her Bachelor’s degree from the Department of Computer Science and Technology, Tsinghua University in 2000. Her research focuses on the spoken dialogue system, prosody and automatic speech recognition. XU Mingxing is currently an lecturer of Tsinghua University. He received his B.S., M.S. and Ph.D. degrees from Tsinghua University, Beijing, China, in 1995, 1997 and 1999 respectively. In 1999, he became a lecturer in the Department of Computer Science, Tsinghua University. Dr.Xu has been working in the area of speech recognition and understanding at the Department of Computer Science and Technology, Tsinghua University, since 1994, and now is with the State Key Laboratory of Intelligent Technology and Systems. His research interests include acoustic and language modelling, speaker identification, keywork spotting, robust speech recognition, dialog system and human-machine interactive system. Dr. Xu is a member of Chinese Information Processing Society of China, a member of the International Speech Communication Association. He served as a Co-Chair of Organizing Committee for the International Symposium on Chinese Spoken Language Processing (ISCSLP’2000), October 2000, Beijing, and Co-Chair of Program Committee for the National Conference on Man-Machine Speech Communications (NCMMSC6) of China, November 2001, Shenzhen.