858 citations
- University of Chinese Academy of SciencesCN34 papers
- Chinese Academy of SciencesCN31 papers
- Institute of AutomationCN24 papers
- Tsinghua UniversityCN24 papers
- Peking UniversityCN19 papers
- Shanghai Artificial Intelligence LaboratoryCN15 papers
- Shandong Institute of AutomationCN14 papers
- Beihang UniversityCN11 papers
- Center for Excellence in Brain Science and Intelligence TechnologyCN8 papers
- Chinese University of Hong KongHK6 papers
- Renmin University of ChinaCN6 papers
- Tencent (China)CN6 papers
18 papers · 1 filter
Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems
Kai Hua, Zhiyuan Feng, Chongyang Tao +2
Recently, knowledge-grounded conversations in the open domain gain great attention from researchers. Existing works on retrieval-based dialogue systems have paid tremendous efforts…
Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing
Yiqun Zhang, Hao Li, Jianhao Chen +4
Balancing performance and efficiency is a central challenge in large language model (LLM) advancement. GPT-5 addresses this with test-time routing, dynamically assigning queries to…
CSDS: A Fine-Grained Chinese Dataset for Customer Service Dialogue Summarization
Haitao Lin, Liqun Ma, Junnan Zhu +4
Dialogue summarization has drawn much attention recently. Especially in the customer service domain, agents could use dialogue summaries to help boost their works by quickly knowin…
Deep Active Learning for Text Classification with Diverse Interpretations
Qiang Liu, Yanqiao Zhu, Zhaocheng Liu +2
Recently, Deep Neural Networks (DNNs) have made remarkable progress for text classification, which, however, still require a large number of labeled data. To train high-performing…
Robust Transfer Learning with Pretrained Language Models through Adapters
Wenjuan Han, Bo Pang, Yingnian Wu
Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language mod…
Alternated Training with Synthetic and Authentic Data for Neural Machine Translation
Rui Jiao, Zonghan Yang, Maosong Sun +1
While synthetic bilingual corpora have demonstrated their effectiveness in low-resource neural machine translation (NMT), adding more synthetic data often deteriorates translation…