2 citations · 4 across the 7 of their papers we have counts for
4 papers · 1 filter
Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization
Ruipeng Jia, Xingxing Zhang, Yanan Cao +3
In zero-shot multilingual extractive text summarization, a model is typically trained on English summarization dataset and then applied on summarization datasets of other languages…
Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation
Yuanxin Liu, Fandong Meng, Zheng Lin +2
Recently, knowledge distillation (KD) has shown great success in BERT compression. Instead of only learning from the teacher's soft label as in conventional KD, researchers find th…
ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques
Yuanxin Liu, Zheng Lin, Fengcheng Yuan
Pre-trained language models of the BERT family have defined the state-of-the-arts in a wide range of NLP tasks. However, the performance of BERT-based models is mainly driven by th…
Learning Class-Transductive Intent Representations for Zero-shot Intent Detection
Qingyi Si, Yuanxin Liu, Peng Fu +3
Zero-shot intent detection (ZSID) aims to deal with the continuously emerging intents without annotated training data. However, existing ZSID systems suffer from two limitations: 1…