面向任务口语对话系统中期待模型的实现算法

刘蓓; 杜利民; 于水源

面向任务口语对话系统中期待模型的实现算法

计量
- 文章访问数: 2032
- HTML全文浏览量: 102
- PDF下载量: 704
- 被引次数: 0
出版历程
- 收稿日期: 2003-05-23
- 修回日期: 2003-12-26
- 刊出日期: 2004-11-19

The Construction of Expectation Model in Task-Oriented Spoken Dialogue Systems and Its Realization Algorithms

摘要

摘要: 该文研究如何从口语对话系统特定场景的期待内容中，抽象出期待所需要的一般的数据结构和处理方法，提出了基于任务模型的期待模型的构建算法．将该期待模型与对话上历史相结合，可以为系统构造出随对话过程动态改变的语境，使系统具备初步地利用语境推导用户意向的推理功能，从而大大提高语义分析的鲁棒性及对话成功率．最后给出了该期待模型在实验系统中应用的有效性结果．
- 口语对话系统;期待;任务模型;算法
Abstract: This paper mainly studies how to extract the common structure and process methods of expectation from scene-specified expectation setting, then puts forbh the algo-rithms to build expectation model suitable for dialogue systems based on the task model. When incorporated with dialog context, this model could create dynamic situation that varies with, dialogue process, which endows the system with the preliminary ability to reason users intentions by reference to this situation, so as to improve the robustness and precision of semantic analysis and the dialogue success rate. Finally, the experimental results prove the effectiveness and usability of this model.

HTML全文

参考文献(1)

Smith B W. Spoken Natural Language Dialogue System: A Practical Approach. London: Oxford University Press, 1994: 144-150.[2]何兆熊.新编语用学概要.上海:上海外语教育出版社,2000,第1章.[3]Grosz B J, Sidner C L. Attention, intentions, and the structure of discourse. Computational Linguistics, 1986, 12(3): 175-204.[4]Mast M, Kummert F, et al.. A speech understanding and dialog system with a homogeneous linguistic knowledge base. IEEE Trans. on Pattern and Machine Intellegence, 1994, PAMI-16(2):179-194.[5]Norbert Reithinger. Experiments in speech act prediction. In Proc. of the AAAI-95 Spring Symposium on Empirical Methods in Discourse, Menlo Park, CA, 1995: 126-131.[6]Popovici C.[J].Baggia P. Specialized language models using dialogue predictions. in Proc. on ICASSP97, Munich, Germany.1997,:-[7]Zhang G L.[J].Yan P J, et al.. An automatic speech recognition strategy directed by the semantic knowledge in dialog system. ISCSLP02, Taipei, China.2002,:-[8]Souvignier B, Kellner A, et al.. The thoughtful elephant: strategies for spoken dialog systems[J].IEEE Trans. on Speech Audio Processing.2000, 8(1):51-62[9]Fink P E, Biermann A W. The correction of ill-formed input using history-based expectation with applications to speech understanding. Computational Linguistics, 1986, 12(1): 13-36.[10]Cleo Jullien, Jean-Charles Marty. Plan revision in person-machine dialogue. 4th EACL Conference, UK, 1989: 153-160.[11]Young S. Talking to machines (statistically speaking). in Proc. ICSLP02, Denver, USA, 2002:9-16.[12]Wang X F.[J].Du L M. The strategy of speech management in a mixed initiative Chinese spoken dialogue system engine. in Proc. ISCSLP00, Beijing, China.2000,:-[13]Komatani K.[J].et al.. Domain-independent spoken dialogue platform using key-phrase spotting based on combined language model. Eurospeech01, Scandinavia.2001,:-

施引文献

资源附件(0)

访问统计