output
20192026
most citedREFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs

858 citations

Showing cs.CLShow all

18 papers · 1 filter

cs.CL202528 cited

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…

cs.CL20252 cited

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…

cs.CL20214 cited

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…

cs.CL202113 cited

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…

cs.CL20212 cited

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…

cs.CL20211 cited

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…