765 citations · 905 across the 19 of their papers we have counts for
7 papers · 1 filter
Robust Lottery Tickets for Pre-trained Language Models
Rui Zheng, Rong Bao, Yuhao Zhou +6
Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching acc…
PATS: Sensitivity-aware Noisy Learning for Pretrained Language Models
Yupeng Zhang, Hongzhi Zhang, Sirui Wang +2
A wide range of NLP tasks benefit from the fine-tuning of pretrained language models (PLMs). However, a number of redundant parameters which contribute less to the downstream task…
Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion
Jian Song, Di Liang, Rumei Li +5
Transformer-based pre-trained models like BERT have achieved great progress on Semantic Sentence Matching. Meanwhile, dependency prior knowledge has also shown general benefits in…
DABERT: Dual Attention Enhanced BERT for Semantic Matching
Sirui Wang, Di Liang, Jian Song +2
Transformer-based pre-trained language models such as BERT have achieved remarkable results in Semantic Sentence Matching. However, existing models still suffer from insufficient a…
Let Me Check the Examples: Enhancing Demonstration Learning via Explicit Imitation
Sirui Wang, Kaiwen Wei, Hongzhi Zhang +2
Demonstration learning aims to guide the prompt prediction via providing answered demonstrations in the few shot settings. Despite achieving promising results, existing work only c…
Searching for Optimal Subword Tokenization in Cross-domain NER
Ruotian Ma, Yiding Tan, Xin Zhou +6
Input distribution shift is one of the vital problems in unsupervised domain adaptation (UDA). The most popular UDA approaches focus on domain-invariant representation learning, tr…
InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NER
Liwen Wang, Rumei Li, Yang Yan +4
Recently, prompt-based methods have achieved significant performance in few-shot learning scenarios by bridging the gap between language model pre-training and fine-tuning for down…