HLT-L2: Language Modeling |
| Session Type: Lecture |
| Time: Friday, 8 May, 08:00 - 10:00 |
| Location: On-Demand |
| Virtual Session: View on Virtual Platform |
| Session Chair: Helen Meng, The Chinese University of Hong Kong |
| HLT-L2.1: AN EMPIRICAL STUDY OF TRANSFORMER-BASED NEURAL LANGUAGE MODEL ADAPTATION |
| Ke Li; Johns Hopkins University |
| Zhe Liu; Facebook |
| Tianxing He; Massachusetts Institute of Technology |
| Hongzhao Huang; Facebook |
| Fuchun Peng; Facebook |
| Daniel Povey; [None] |
| Sanjeev Khudanpur; Johns Hopkins University |
| HLT-L2.2: LOW-BIT QUANTIZATION OF RECURRENT NEURAL NETWORK LANGUAGE MODELS USING ALTERNATING DIRECTION METHODS OF MULTIPLIERS |
| Junhao Xu; Chinese University of Hong Kong |
| Xie Chen; Microsoft |
| Shoukang Hu; Chinese University of Hong Kong |
| Jianwei Yu; Chinese University of Hong Kong |
| Xunying Liu; Chinese University of Hong Kong |
| Helen Meng; Chinese University of Hong Kong |
| HLT-L2.3: AUDIO-ATTENTION DISCRIMINATIVE LANGUAGE MODEL FOR ASR RESCORING |
| Ankur Gandhe; Amazon, Inc. |
| Ariya Rastrow; Amazon, Inc. |
| HLT-L2.4: TRAINING CODE-SWITCHING LANGUAGE MODEL WITH MONOLINGUAL DATA |
| Shun-Po Chuang; National Taiwan University |
| Tzu-Wei Sung; University of California, San Diego |
| Hung-Yi Lee; National Taiwan University |
| HLT-L2.5: DOMAIN ROBUST, FAST, AND COMPACT NEURAL LANGUAGE MODELS |
| Alexander Gerstenberger; RWTH Aachen University |
| Kazuki Irie; RWTH Aachen University |
| Pavel Golik; AppTek GmbH |
| Eugen Beck; RWTH Aachen University |
| Hermann Ney; RWTH Aachen University |
| HLT-L2.6: A RANDOM GOSSIP BMUF PROCESS FOR NEURAL LANGUAGE MODELING |
| Yiheng Huang; Tencent |
| Jinchuan Tian; Tencent |
| Lei Han; Tencent |
| Guangsen Wang; Tencent |
| Xingchen Song; Tsinghua University |
| Dan Su; Tencent |
| Dong Yu; Tencent |