限定领域口语对话系统中超出领域话语的协处理方法

王俊东,黄沛杰,林仙茂,徐禹洪,李凯茵

PDF(5776 KB)
PDF(5776 KB)
中文信息学报 ›› 2015, Vol. 29 ›› Issue (5) : 194-204.
自然语言处理应用

限定领域口语对话系统中超出领域话语的协处理方法

  • 王俊东,黄沛杰,林仙茂,徐禹洪,李凯茵
作者信息 +

A Coprocessor for Out-of-Domain Utterances in Domain Specific Spoken Dialogue System

  • WANG Jundong, HUANG Peijie, LIN Xianmao, XU Yuhong, LI Kaiyin
Author information +
History +

摘要

领域外话语的开放性、口语化以及表达多样性,使得现有的限定领域口语对话系统不能很好地处理超出领域话语。该文提出了一种限定领域口语对话系统协处理方案,基于人工智能标记语言AIML,设计一套理解开放语义用户话语的理解模板,并对未匹配话语基于话语相似度进行理解模板分类,进而采用扩展有限状态自动机处理模式,结合对话流程上下文的状态及信息,实现理解模板到应答模板的转换,改变了单纯模板匹配方法在对话流程控制方面的相对缺失。中文手机导购领域的测试表明,该文所提出的协处理方法能有效地辅助口语对话系统完成限定领域完整对话流程,得到更好的用户满意度。

Abstract

The openness, colloquialism and diversity of out-of-domain (OOD) utterances make them difficult to the domain specific spoken dialogue system. This paper tackles this problem by proposing a coprocessor for domain specific dialogue system. Based on the artificial intelligence markup language(AIML), open semantic understanding templates are designed, and understanding template classification is used to address the unmatched OOD utterances. Then the extended finite state machine (EFSM) is adopted to transform the understanding template into answering template and realize the control of the state and information of the dialogue process. The application in mobile phone shopping guide domain shows that the proposed coprocessor can effectively help the Chinese dialogue system to finish the dialogue process and get better user experience.

关键词

超出领域话语 / 协处理 / AIML / 有限状态自动机 / 口语对话系统

Key words

out-of-domain utterance / coprocessor / AIML / FSM / spoken dialogue system

引用本文

导出引用
王俊东,黄沛杰,林仙茂,徐禹洪,李凯茵. 限定领域口语对话系统中超出领域话语的协处理方法. 中文信息学报. 2015, 29(5): 194-204
WANG Jundong, HUANG Peijie, LIN Xianmao, XU Yuhong, LI Kaiyin. A Coprocessor for Out-of-Domain Utterances in Domain Specific Spoken Dialogue System. Journal of Chinese Information Processing. 2015, 29(5): 194-204

参考文献

[1] Price P J. Evaluation of spoken language systems: the ATIS domain[C]//Proceedings of DARPA Workshop on Speech and Natural Language, Hidden Valley, PA, 1990.
[2] Gorin A, Riccardi G, Wright J. How may I help you?[J]. Speech Communication,1997, 23(1-2): 113-127.
[3] Zue V, Seneff S, Glass J, et al. JUPITER: a telephone-based conversational interface for weather information[J]. IEEE Transactions on Speech and Audio Processing, 2000, 8(1): 85-96.
[4] 黄寅飞, 郑方, 燕鹏举等. 校园导航系统EasyNav的设计与实现[J].中文信息学报, 2001, 15(4): 35-40.
[5] Durston P, Farrell M, Attwater D, et al. OASIS natural language call steering trial[C]//Proceedings of 7th European Conference on Speech Communication and Technology (Eurospeech 2011), 2001: 1323-1326.
[6] 张琳, 高峰, 郭荣等. 汉语股票实时行情查询对话系统[J]. 计算机应用, 2004, 24(7): 61-63.
[7] Pappu A, Rudnicky A. The structure and generality of spoken route instructions[C]//Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2012), 2012: 99-107.
[8] Reichel C S, Sohn J, Ehrlich U, et al. Out-of-domain spoken dialogs in the car: a WoZ study[C]//Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2014), 2014: 12-21.
[9] Wallace R S. A.L.I.C.E. artificial intelligence foundation[EB/OL]. [2015-08-10]. http://www.alicebot.org.
[10] Banchs R E, Li H. IRIS: a chat-oriented dialogue system based on the vector space model[C]//Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (ACL 2012), demo session.
[11] Mollá D, González J L V. Question answering in restricted domains: an overview[J]. Computational Linguistics, 2007, 33(1): 41-61
[12] Ameixa D, Coheur L, Fialho P, et al. Luke, I am your father: dealing with out-of-domain requests by using movies subtitles [J]. LNCS (LNAI), (8637): 13-21.
[13] Metallinou A, Bohus D, Williams J D. Discriminative state tracking for spoken dialog systems[C]//Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013), 2013: 466-475.
[14] Xu W Q, Xu B, Huang T Y, et al. Bridging the gap between dialogue management and dialogue models[C]//Proceedings of the Third SIGdial Workshop on Discourse and Dialogue (SIGDIAL 2002), 2002: 201-210.
[15] 邬晓钧, 郑方, 徐明星. 基于主题森林结构的对话管理模型[J]. 自动化学报, 2003,29(2):275-283.
[16] Peltason J, Wrede B. Pamini: a framework for assembling mixed-initiative human-robot interaction from generic interaction patterns[C]//Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2010), 2010: 229-232.
[17] Lane I R, Kawahara T, Matsui T, et al. Out-of-domain utterance detection using classification confidences of multiple topics[J]. IEEE Transactions on Audio, Speech, and Language Processing, 2007, 15(1):150-161.
[18] Tür G, Deoras A, Hakkani-Tür D. Detecting out-of-domain utterances addressed to a virtual personal assistant[C]//Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014), 2014: 283-287.
[19] Celikyitmaz A, Hakkani-Tür D, Tür G. Approximate inference for domain detection in spoken language understanding[C]//Proceedings of the 12th Annual Conference of the International Speech Communication Association (INTERSPEECH 2011), 2011: 1293-1296.
[20] Weizenbaum J. ELIZA-a computer program for the study of natural language communication between man and machine[J]. Communications of the ACM, 1966, 9(1):36-45.
[21] Colby K M, Weber S, Hilf F D. Artificial paranoia[J]. Artificial Intelligence, 1971, 2(1): 1-25.
[22] Schumaker R P, Chen H. Interaction analysis of the ALICE chatterbot: a two-study investigation of dialog and domain questioning[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part A, 2010, 40(1): 40-51.
[23] 清华大学图书馆智能机器人小图[EB/OL]. [2015-08-10]. http://166.111.120.164:8081/programd/.
[24] 小I机器人[EB/OL]. [2015-08-10]. http://www.xiaoi.com/index.html.
[25] Schumaker R P, Chen H. Leveraging question answer technology to address terrorism inquiry[J]. Decision Support Systems, 2007, 43(4): 1419-1430.
[26] Jia J Y. CSIEC: a computer assisted English learning chatbot based on textual knowledge and reasoning[J]. Knowledge-Based Systems, 2009, 22 (4): 249-255.
[27] Crutzen R, Peters G Y, Portugal S D, et al. An artificially intelligent chat agent that answers adolescents questions related to sex, drugs, and alcohol: an exploratory study[J]. Journal of Adolescent Health, 2011, 48(5):514-519.
[28] Huang J Z, Zhou M, Yang D. Extracting chatbot knowledge from online discussion forums[C]//Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI 2007), 2007: 423-428.
[29] Banchs R E. Movie-DiC: a movie dialogue corpus for research and development[C]//Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (ACL 2012), 2012: 203-207.
[30] Wallace R S. The anatomy of A.L.I.C.E. [EB/OL]. [2015-08-10]. http://www.alicebot.org/anatomy.html.
[31] Huang P J, Lin X M, Lian Z Q, et al. Ch2R: a Chinese chatter robot for online shopping guide[C]//Proceedings of the 3rd CIPS-SIGHAN Joint Conference on Chinese Language Processing (CLP-2014), 2014: 26-34.
[32] 黄民烈, 朱小燕. 对话管理中基于槽特征有限状态自动机的方法研究[J]. 计算机学报, 2004, 27 (08): 1092-1101.
[33] Chen Y N, Wang W Y, Rudnicky A. Unsupervised induction and filling of semantic slots for spoken dialogue systems using frame-semantic parsing[C]//Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2013.

王俊东(1992—),硕士研究生,主要研究领域为自然语言处理。
E-mail: jdwang@stu.scau.edu.cn黄沛杰(1980—),通信作者,博士,副教授,主要研究领域为人工智能、自然语言处理、口语对话系统。
E-mail: pjhuang@scau.edu.cn林仙茂(1990—),本科,主要研究领域为口语对话系统。
E-mail: xianmaulin@gmail.com
(上接第184页)

[20] Tomas Mikolov, Wen-tau Yih, Geoffrey Zweig. Linguistic Regularities in Continuous Space Word Representations[C]//Proceedings of NAACL HLT, 2013:746-751.

基金

国家自然科学基金(71472068);广东省大学生创新训练计划项目(201410564290,201510564281)
PDF(5776 KB)

538

Accesses

0

Citation

Detail

段落导航
相关文章

/