Modelling Human Clarification Strategies
作者： Julia Hirschberg , Svetlana Stoyanchev , Alex Liu
DOI:
关键词:
摘要: We model human responses to speech recognition errors from a corpus of clarification strategies. employ learning techniques study 1) the decision either stop and ask question or continue dialogue without clarification, 2) targeted more generic question. Targeted questions focus specifically on part an utterance that is misrecognized, in contrast with requests ‘please repeat’ rephrase’. Our goal generate strategies for handling spoken systems, when appropriate. experiments show linguistic features, particular inferred part-ofspeech misrecognized word are predictive decisions. A combination features predicts user’s accuracy 72.8% over majority baseline 59.1%. The same set predict 74.6% compared 71.8%. 1
aclweb.org
columbia.edu 参考文章(13)
Murat Akbacak, Horacio Franco, Michael Frandsen, Sasa Hasan, Huda Jameel, Andreas Kathol, Shahram Khadivi, Xin Lei, Arindam Mandal, Saab Mansour, Kristin Precoda, Colleen Richey, Dimitra Vergyri, Wen Wang, Mei Yang, Jing Zheng, Recent advances in SRI'S IraqComm™ Iraqi Arabic-English speech-to-speech translation system international conference on acoustics, speech, and signal processing. pp. 4809- 4812 ,(2009) , 10.1109/ICASSP.2009.4960707
Dan Bohus, Brian Langner, Antoine Raux, Alan Black, Maxine Eskenazi, Alex Rudnicky, ONLINE SUPERVISED LEARNING OF NON-UNDERSTANDING RECOVERY POLICIES spoken language technology workshop. pp. 170- 173 ,(2006) , 10.1109/SLT.2006.326844
Yuichiro Fukubayashi, Tetsuya Ogata, Kazunori Komatani, Hiroshi G. Okuno, Dynamic Help Generation by Estimating User's Mental Model in Spoken Dialogue Systems conference of the international speech communication association. pp. 1946- 1949 ,(2006)
Steve J. Young, Jason D. Williams, Characterizing task-oriented dialog using a simulated ASR chanel. conference of the international speech communication association. ,(2004)
Mark A. Hall, Ian H. Witten, Eibe Frank, Data Mining: Practical Machine Learning Tools and Techniques ,(1999)
Alexander I. Rudnicky, Dan Bohus, A Principled Approach for Rejection Threshold Optimization in Spoken Dialog Systems conference of the international speech communication association. pp. 2781- 2784 ,(2005)
Theodora Koulouri, Stanislao Lauria, Exploring Miscommunication and Collaborative Behaviour in Human-Robot Interaction annual meeting of the special interest group on discourse and dialogue. pp. 111- 119 ,(2009) , 10.3115/1708376.1708391
Kristina Toutanova, Dan Klein, Christopher D. Manning, Yoram Singer, Feature-rich part-of-speech tagging with a cyclic dependency network Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - NAACL '03. pp. 173- 180 ,(2003) , 10.3115/1073445.1073478
Svetlana Stoyanchev, Philipp Salletmayr, Jingbo Yang, Julia Hirschberg, Localized detection of speech recognition errors spoken language technology workshop. pp. 25- 30 ,(2012) , 10.1109/SLT.2012.6424164
Gabriel Skantze, Exploring human error recovery strategies: Implications for spoken dialogue systems Speech Communication. ,vol. 45, pp. 325- 341 ,(2005) , 10.1016/J.SPECOM.2004.11.005