activity
20172020
most citedLabel Embedding Network: Learning Label Representation for Soft Training of Deep Networks

31 citations · 87 across the 9 of their papers we have counts for

collaborators
Showing 2017Show all

6 papers · 1 filter

cs.LG2017★ 6 cited

Complex Structure Leads to Overfitting: A Structure Regularization Decoding Method for Natural Language Processing

Xu Sun, Weiwei Sun, Shuming Ma +4

Recent systems on structured prediction focus on increasing the level of structural dependencies within the model. However, our study suggests that complex structures entail high o…

cs.LG2017★ 31 cited

Label Embedding Network: Learning Label Representation for Soft Training of Deep Networks

Xu Sun, Bingzhen Wei, Xuancheng Ren +1

We propose a method, called Label Embedding Network, which can learn label representation (label embedding) during the training process of deep networks. With the proposed method,…

cs.CL2017★ 19 cited

A Semantic Relevance Based Neural Network for Text Summarization and Text Simplification

Shuming Ma, Xu Sun

Text summarization and text simplification are two major ways to simplify the text for poor readers, including children, non-native speakers, and the functionally illiterate. Text…

cs.CL2017★ 5 cited

Improving Semantic Relevance for Sequence-to-Sequence Learning of Chinese Social Media Text Summarization

Shuming Ma, Xu Sun, Jingjing Xu +3

Current Chinese social media text summarization models are based on an encoder-decoder framework. Although its generated summaries are similar to source texts literally, they have…

cs.CL2017★ 1 cited

A Generic Online Parallel Learning Framework for Large Margin Models

Shuming Ma, Xu Sun

To speed up the training process, many existing systems use parallel technology for online learning algorithms. However, most research mainly focus on stochastic gradient descent (…

cs.CL2017

Lock-Free Parallel Perceptron for Graph-based Dependency Parsing

Xu Sun, Shuming Ma

Dependency parsing is an important NLP task. A popular approach for dependency parsing is structured perceptron. Still, graph-based dependency parsing has the time complexity of $O…