activity
20182024
most citedFedKD: Communication Efficient Federated Learning via Knowledge Distillation

623 citations · 1.9k across the 48 of their papers we have counts for

collaborators
Showing 2019Show all

6 papers · 1 filter

cs.DL2019

Legends of Nature and Editors-in-chief

Zhiwen Hu, Chuhan Wu, Zhongliang Yang +1

This year marks the 150th celebration of Nature. However, the understanding of the way the army of unsung editors-in-chief has strengthened and enriched the integrity and quality o…

cs.CL2019★ 34 cited

Neural News Recommendation with Attentive Multi-View Learning

Chuhan Wu, Fangzhao Wu, Mingxiao An +3

Personalized news recommendation is very important for online news platforms to help users find interested news and improve user experience. News and user representation learning i…

cs.IR2019★ 315 cited

NPA: Neural News Recommendation with Personalized Attention

Chuhan Wu, Fangzhao Wu, Mingxiao An +3

News recommendation is very important to help users find interested news and alleviate information overload. Different users usually have different interests and the same user may…

cs.IR2019★ 58 cited

NRPA: Neural Recommendation with Personalized Attention

Hongtao Liu, Fangzhao Wu, Wenjun Wang +4

Existing review-based recommendation methods usually use the same model to learn the representations of all users/items from reviews posted by users towards items. However, differe…

cs.CL2019★ 78 cited

Neural Chinese Named Entity Recognition via CNN-LSTM-CRF and Joint Training with Word Segmentation

Fangzhao Wu, Junxin Liu, Chuhan Wu +2

Chinese named entity recognition (CNER) is an important task in Chinese natural language processing field. However, CNER is very challenging since Chinese entity names are highly c…

cs.CL2019★ 9 cited

Neural Chinese Word Segmentation with Lexicon and Unlabeled Data via Posterior Regularization

Junxin Liu, Fangzhao Wu, Chuhan Wu +2

Existing methods for CWS usually rely on a large number of labeled sentences to train word segmentation models, which are expensive and time-consuming to annotate. Luckily, the unl…