4.8k citations
- Peking UniversityCN85 papers
- Microsoft (United States)US82 papers
- Tsinghua UniversityCN81 papers
- University of Science and Technology of ChinaCN81 papers
- Hong Kong University of Science and TechnologyHK40 papers
- Beihang UniversityCN36 papers
- Chinese Academy of SciencesCN36 papers
- Shanghai Jiao Tong UniversityCN33 papers
- Microsoft Research (United Kingdom)GB28 papers
- Zhejiang UniversityCN28 papers
- Fudan UniversityCN24 papers
- Carnegie Mellon UniversityUS19 papers
11 papers · 2 filters
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
Sanyuan Chen, Chengyi Wang, Zhengyang Chen +15
Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks. As speech signal contai…
Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations
Wei Chen, Yeyun Gong, Can Xu +9
We study the problem of coarse-grained response selection in retrieval-based dialogue systems. The problem is equally important with fine-grained response selection, but is less ex…
Task-Oriented Dialogue System as Natural Language Generation
Weizhi Wang, Zhirui Zhang, Junliang Guo +3
In this paper, we propose to formulate the task-oriented dialogue system as the purely natural language generation task, so as to fully leverage the large-scale pre-trained models…
Learning Algebraic Recombination for Compositional Generalization
Chenyao Liu, Shengnan An, Zeqi Lin +6
Neural sequence models exhibit limited compositional generalization ability in semantic parsing tasks. Compositional generalization requires algebraic recombination, i.e., dynamica…
FastSeq: Make Sequence Generation Faster
Yu Yan, Fei Hu, Jiusheng Chen +7
Transformer-based models have made tremendous impacts in natural language generation. However the inference speed is a bottleneck due to large model size and intensive computing in…
EL-Attention: Memory Efficient Lossless Attention for Generation
Yu Yan, Jiusheng Chen, Weizhen Qi +4
Transformer model with multi-head attention requires caching intermediate results for efficient inference in generation tasks. However, cache brings new memory-related costs and pr…