Technical Program

HLT-P2: Topic Modeling and Dialog

Session Type: Poster
Time: Wednesday, May 15, 08:30 - 10:30
Location: Poster Area C, Ground Floor
Session Chair: Chiori Hori, MERL
 
HLT-P2.1: TOPIC DETECTION IN CONVERSATIONAL TELEPHONE SPEECH USING CNN WITH MULTI-STREAM INPUTS
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Jian Sun; University of Science and Technology of China
         Wu Guo; University of Science and Technology of China
         Zhi Chen; University of Science and Technology of China
         Yan Song; University of Science and Technology of China
 
HLT-P2.2: WHY DO NEURAL DIALOG SYSTEMS GENERATE SHORT AND MEANINGLESS REPLIES? A COMPARISON BETWEEN DIALOG AND TRANSLATION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Bolin Wei; Peking University
         Shuai Lu; Peking University
         Lili Mou; University of Waterloo
         Hao Zhou; Toutiao AI Lab
         Pascal Poupart; University of Waterloo
         Ge Li; Peking University
         Zhi Jin; Peking University
 
HLT-P2.3: DEEP HYBRID NETWORKS BASED RESPONSE SELECTION FOR MULTI-TURN DIALOGUE SYSTEMS
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Xishuo Li; Beihang University
         Lijun Zhang; Beihang University
         Wenge Rong; Beihang University
         Baiwen Li; Beihang University
         Qi Li; Beihang University
 
HLT-P2.4: MITIGATING THE IMPACT OF SPEECH RECOGNITION ERRORS ON SPOKEN QUESTION ANSWERING BY ADVERSARIAL DOMAIN ADAPTATION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Chia-Hsuan Lee; National Taiwan University
         Yun-Nung Chen; National Taiwan University
         Hung-Yi Lee; National Taiwan University
 
HLT-P2.5: A HIERARCHICAL DECODING MODEL FOR SPOKEN LANGUAGE UNDERSTANDING FROM UNALIGNED DATA
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Zijian Zhao; Shanghai Jiao Tong University
         Su Zhu; Shanghai Jiao Tong University
         Kai Yu; Shanghai Jiao Tong University
 
HLT-P2.6: EXPLORING ATTENTION MECHANISM FOR ACOUSTIC-BASED CLASSIFICATION OF SPEECH UTTERANCES INTO SYSTEM-DIRECTED AND NON-SYSTEM-DIRECTED
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Atta Norouzian; Nuance Communications
         Bogdan Mazoure; McGill University
         Dermot Connolly; Nuance Communications
         Daniel Willett; Nuance Communications
 
HLT-P2.7: INVESTIGATING THE EFFECTS OF WORD SUBSTITUTION ERRORS ON SENTENCE EMBEDDINGS
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Rohit Voleti; Arizona State University
         Julie Liss; Arizona State University
         Visar Berisha; Arizona State University
 
HLT-P2.8: IMPROVING HUMAN-COMPUTER INTERACTION IN LOW-RESOURCE SETTINGS WITH TEXT-TO-PHONETIC DATA AUGMENTATION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Adam Stiff; The Ohio State University
         Prashant Serai; The Ohio State University
         Eric Fosler-Lussier; The Ohio State University
 
HLT-P2.9: A NOVEL REPETITION NORMALIZED ADVERSARIAL REWARD FOR HEADLINE GENERATION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Peng Xu; The Hong Kong University of Science and Technology
         Pascale Fung; The Hong Kong University of Science and Technology
 
HLT-P2.10: ROLE SPECIFIC LATTICE RESCORING FOR SPEAKER ROLE RECOGNITION FROM SPEECH RECOGNITION OUTPUTS
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Nikolaos Flemotomos; University of Southern California
         Panayiotis Georgiou; University of Southern California
         David Atkins; University of Washington
         Shrikanth Narayanan; University of Southern California