SPE-52.5
MULTI-TASK RNN-T WITH SEMANTIC DECODER FOR STREAMABLE SPOKEN LANGUAGE UNDERSTANDING
Xuandi Fu, Carnegie Mellon University, United States of America; Feng-Ju Chang, Martin Radfar, Kai Wei, Jing Liu, Grant P. Strimel, Kanthashree Mysore Sathyendra, Amazon, United States of America
Session:
Language Understanding II: Context/Knowledge Integration
Track:
Speech and Language Processing
Location:
Gather Area E
Presentation Time:
Wed, 11 May, 20:00 - 20:45 China Time (UTC +8)
Wed, 11 May, 12:00 - 12:45 UTC
Wed, 11 May, 12:00 - 12:45 UTC
Session Chair:
Ryo Masumura, NTT Corporation
Session SPE-52
SPE-52.1: Knowledge Augmented BERT Mutual Network in Multi-turn Spoken Dialogues
Ting-Wei Wu, Biing-Hwang Juang, Georgia Institute of Technology, United States of America
SPE-52.2: TINYS2I: A SMALL-FOOTPRINT UTTERANCE CLASSIFICATION MODEL WITH CONTEXTUAL SUPPORT FOR ON-DEVICE SLU
Anastasios Alexandridis, Kanthashree Mysore Sathyendra, Grant Strimel, Pavel Kveton, Jon Webb, Athanasios Mouchtaris, Amazon.com, United States of America
SPE-52.3: TOWARDS END-TO-END INTEGRATION OF DIALOG HISTORY FOR IMPROVED SPOKEN LANGUAGE UNDERSTANDING
Vishal Sunder, Eric Fosler-Lussier, The Ohio State University, United States of America; Samuel Thomas, Hong-Kwang Kuo, Jatin Ganhotra, Brian Kingsbury, IBM, United States of America
SPE-52.4: IMPROVING SPOKEN LANGUAGE UNDERSTANDING BY ENHANCING TEXT REPRESENTATION
Thai Binh Nguyen, Karlsruhe Institute of Technology, Germany
SPE-52.5: MULTI-TASK RNN-T WITH SEMANTIC DECODER FOR STREAMABLE SPOKEN LANGUAGE UNDERSTANDING
Xuandi Fu, Carnegie Mellon University, United States of America; Feng-Ju Chang, Martin Radfar, Kai Wei, Jing Liu, Grant P. Strimel, Kanthashree Mysore Sathyendra, Amazon, United States of America
SPE-52.6: A BERT based Joint Learning Model with Feature Gated Mechanism for Spoken Language Understanding
Wang Zhang, Lei Jiang, Shaokang Zhang, Shuo Wang, Jianlong Tan, Chinese Academic of Science, China