SDS: Spoken Dialog Systems |
| Session Type: Poster |
| Time: Wednesday, December 18, 10:30 - 12:00 |
| Location: VHS Event Centre, Level 1 |
| Session Chair: Rohan Kumar Das, National University of Singapore |
| SDS.1: ROBUST BELIEF STATE SPACE REPRESENTATION FOR STATISTICAL DIALOGUE MANAGERS USING DEEP AUTOENCODERS |
| Fotios Lygerakis, Vassilios Diakoloulas, Michail Lagoudakis, Technical University of Crete, Greece; Kotti Margarita, Toshiba Research Cambridge, United Kingdom |
| SDS.2: IMPROVING SPEECH-BASED END-OF-TURN DETECTION VIA CROSS-MODAL　REPRESENTATION LEARNING WITH PUNCTUATED TEXT DATA |
| Ryo Masumura, Mana Ihori, Tomohiro Tanaka, Atsushi Ando, Ryo Ishii, Takanobu Oba, Ryuichiro Higashinaka, NTT Corporation, Japan |
| SDS.3: DIALOGUE ENVIRONMENTS ARE DIFFERENT FROM GAMES: INVESTIGATING VARIANTS OF DEEP Q-NETWORKS FOR DIALOGUE POLICY |
| Yu-An Wang, Yun-Nung Chen, National Taiwan University, Taiwan |
| SDS.4: EFFICIENT SEMI-SUPERVISED LEARNING FOR NATURAL LANGUAGE UNDERSTANDING BY OPTIMIZING DIVERSITY |
| Eunah Cho, He Xie, Alexa AI, United States; John Lalor, University of Notre Dame, United States; Varun Kumar, William M. Campbell, Alexa AI, United States |