HLT-P1: Spoken Language Understanding and Dialogue I |
Session Type: Poster |
Time: Wednesday, 6 May, 16:30 - 18:30 |
Location: On-Demand |
Virtual Session: View on Virtual Platform |
Session Chair: Andreas Stolcke, Amazon |
HLT-P1.1: A HIERARCHICAL MODEL FOR DIALOG ACT RECOGNITION CONSIDERING ACOUSTIC AND LEXICAL CONTEXT INFORMATION |
Yuke Si; Tianjin University |
Longbiao Wang; Tianjin University |
Jianwu Dang; Tianjin University |
Mengfei Wu; Tianjin University |
Aijun Li; Chinese Academy of Social Science |
HLT-P1.2: LARGE-SCALE UNSUPERVISED PRE-TRAINING FOR END-TO-END SPOKEN LANGUAGE UNDERSTANDING |
Pengwei Wang; Alibaba |
Liangchen Wei; Alibaba |
Yong Cao; Alibaba |
Jinghui Xie; Alibaba |
Zaiqing Nie; Alibaba |
HLT-P1.3: IMPROVING SPOKEN QUESTION ANSWERING USING CONTEXTUALIZED WORD REPRESENTATION |
Dan Su; Hong Kong University of Science and Technology |
Pascale Fung; Hong Kong University of Science and Technology |
HLT-P1.4: LEARNING ASR-ROBUST CONTEXTUALIZED EMBEDDINGS FOR SPOKEN LANGUAGE UNDERSTANDING |
Chao-Wei Huang; National Taiwan University |
Yun-Nung Chen; National Taiwan University |
HLT-P1.5: A HIERARCHICAL TRACKER FOR MULTI-DOMAIN DIALOGUE STATE TRACKING |
Jieyu Li; Shanghai Jiao Tong University |
Su Zhu; Shanghai Jiao Tong University |
Kai Yu; Shanghai Jiao Tong University |
HLT-P1.6: A BI-MODEL APPROACH FOR HANDLING UNKNOWN SLOT VALUES IN DIALOGUE STATE TRACKING |
Yu Wang; Samsung Research America |
Yilin Shen; Samsung Research America |
Hongxia Jin; Samsung Research America |
HLT-P1.7: IMPROVING SAMPLE-EFFICIENCY IN REINFORCEMENT LEARNING FOR DIALOGUE SYSTEMS BY USING TRAINABLE-ACTION-MASK |
Yen-Chen Wu; Cambridge University |
Bo-Hsiang Tseng; Cambridge University |
Carl Edward Rasmussen; Cambridge University |
HLT-P1.8: FG2SEQ: EFFECTIVELY ENCODING KNOWLEDGE FOR END-TO-END TASK-ORIENTED DIALOG |
Zhenhao He; South China University of Technology |
Yuhong He; South China Agricultural University |
Qingyao Wu; South China University of Technology |
Jian Chen; South China University of Technology |
HLT-P1.9: A SIMPLE BUT EFFECTIVE BERT MODEL FOR DIALOG STATE TRACKING ON RESOURCE-LIMITED SYSTEMS |
Tuan Lai; Purdue University |
Quan Tran; Adobe Research |
Trung Bui; Adobe Research |
Daisuke Kihara; Purdue University |
HLT-P1.10: FAST DOMAIN ADAPTATION FOR GOAL-ORIENTED DIALOGUE USING A HYBRID GENERATIVE-RETRIEVAL TRANSFORMER |
Igor Shalyminov; Heriot-Watt University |
Alessandro Sordoni; Microsoft Research Montréal |
Adam Atkinson; Microsoft Research Montréal |
Hannes Schulz; Microsoft Research Montréal |
HLT-P1.11: PREDICTING PERFORMANCE OUTCOME WITH A CONVERSATIONAL GRAPH CONVOLUTIONAL NETWORK FOR SMALL GROUP INTERACTIONS |
Yun-Shao Lin; National Tsing Hua University |
Chi-Chun Lee; National Tsing Hua University |
HLT-P1.12: DESIGN CONSIDERATIONS FOR HYPOTHESIS REJECTION MODULES IN SPOKEN LANGUAGE UNDERSTANDING SYSTEMS |
Aman Alok; Amazon.com Services Inc. |
Rahul Gupta; Amazon.com Services Inc. |
Shankar Ananthakrishnan; Amazon.com Services Inc. |