Multitask Learning for Spoken Language Understanding
作者： G. Tur
DOI: 10.1109/ICASSP.2006.1660088
关键词: Spoken dialog systems 、 Machine learning 、 Natural language processing 、 Goal orientation 、 Representation (mathematics) 、 Active learning 、 Spoken language 、 Task (project management) 、 Multi-task learning 、 Speech processing 、 Artificial intelligence 、 Active learning (machine learning) 、 Computer science
摘要: In this paper, we present a multitask learning (MTL) method for intent classification in goal oriented human-machine spoken dialog systems. MTL aims at training tasks parallel while using shared representation. What is learned each task can help other be better. Our to automatically re-use the existing labeled data from various applications, which are similar but may have different intents or distributions, order improve performance. For purpose, propose an automated mapping algorithm across applications. We also employing active selectively sample re-used. results indicate that achieve significant improvements performance especially when size limited.
lens.org 参考文章(24)
Shahla Parveen, Phil D. Green, Multitask learning in connectionist robust ASR using recurrent neural networks. conference of the international speech communication association. ,(2003)
Dilek Z. Hakkani-Tur, Gokhan Tur, Ananlada Chotimongkol, System and method of semi-supervised learning for spoken language understanding using semantic role labeling ,(2012)
Dilek Z. Hakkani-Tur, Jeremy Huntley Wright, Giuseppe Riccardi, Gokhan Tur, Allen Louis Gorin, System and method of spoken language understanding using word confusion networks ,(2009)
Dilek Z. Hakkani-Tur, Giuseppe Riccardi, Allen Louis Gorin, Method of Active Learning for Automatic Speech Recognition ,(2014)
Dilek Z. Hakkani-Tur, Mazin G. Rahim, Gokhan Tur, Active labeling for spoken language understanding conference of the international speech communication association. ,(2009)
Dilek Zeynep Hakkani-Tur, Giuseppe Riccardi, System and Method for Unsupervised and Active Learning for Automatic Speech Recognition ,(2011)
Mazin G. Rahim, Gokhan Tur, Antony Van der Mude, Narendra K. Gupta, Method for building a natural language understanding model for a spoken dialog system ,(2009)
Robert D'Angelo, Christopher Gindel, James Hirni, Bruce Cottle, Michael Ely, Telephony system for conducting multimedia telephonic conferences over a packet-based network ,(1999)
Angelo Salvucci, Kurt E. Warner, William C. Cook, Don E. Reich, Real-time incident and response information messaging in a system for the automatic notification that an emergency call has occurred from a wireless telecommunication device ,(2003)