1.8k citations
- Peking UniversityCN36 papers
- Sun Yat-sen UniversityCN19 papers
- Harbin Institute of TechnologyCN18 papers
- University of Chinese Academy of SciencesCN16 papers
- Tsinghua UniversityCN15 papers
- Beihang UniversityCN13 papers
- Southern University of Science and TechnologyCN13 papers
- Chinese Academy of SciencesCN12 papers
- Tencent (China)CN11 papers
- Beijing Jiaotong UniversityCN8 papers
- Institute of Computing TechnologyCN8 papers
- South China University of TechnologyCN8 papers
5 papers · 1 filter
A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation
Chulun Zhou, Yunlong Liang, Fandong Meng +5
Neural chat translation (NCT) aims to translate a cross-lingual chat between speakers of different languages. Existing context-aware NMT models cannot achieve satisfactory performa…
You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient
Shaokun Zhang, Xiawu Zheng, Chenyi Yang +7
Despite superior performance on various natural language processing tasks, pre-trained models such as BERT are challenged by deploying on resource-constraint devices. Most existing…
Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker
Runxin Xu, Tianyu Liu, Lei Li +1
Document-level event extraction aims to recognize event information from a whole piece of article. Existing methods are not effective due to two challenges of this task: a) the tar…
Abstractive Opinion Tagging
Qintong Li, Piji Li, Xinyi Li +3
In e-commerce, opinion tags refer to a ranked list of tags provided by the e-commerce platform that reflect characteristics of reviews of an item. To assist consumers to quickly gr…
How Does Selective Mechanism Improve Self-Attention Networks?
Xinwei Geng, Longyue Wang, Xing Wang +3
Self-attention networks (SANs) with selective mechanism has produced substantial improvements in various NLP tasks by concentrating on a subset of input words. However, the underly…