activity
20172019
most citedMulti-level Gated Recurrent Neural Network for Dialog Act Classification

12 citations · 35 across the 5 of their papers we have counts for

collaborators
Showing cs.CLShow all

11 papers · 1 filter

cs.CL201912 cited

Multi-level Gated Recurrent Neural Network for Dialog Act Classification

Wei Li, Yunfang Wu

In this paper we focus on the problem of dialog act (DA) labelling. This problem has recently attracted a lot of attention as it is an important sub-part of an automatic question a…

cs.CL2019

Recursive Graphical Neural Networks for Text Classification

Wei Li, Shuheng Li, Shuming Ma +3

The complicated syntax structure of natural language is hard to be explicitly modeled by sequence-based models. Graph is a natural structure to describe the complicated relation be…

cs.CL20199 cited

Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model

Wei Li, Jingjing Xu, Yancheng He +3

Automatic article commenting is helpful in encouraging user engagement and interaction on online news platforms. However, the news documents are usually too long for traditional en…

cs.CL2018

Learning Universal Sentence Representations with Mean-Max Attention Autoencoder

Minghua Zhang, Yunfang Wu, Weikang Li +1

In order to learn universal sentence representations, previous methods focus on complex recurrent neural networks or supervised learning. In this paper, we propose a mean-max atten…

cs.CL2018

Sememe Prediction: Learning Semantic Knowledge from Unstructured Textual Wiki Descriptions

Wei Li, Xuancheng Ren, Damai Dai +3

Huge numbers of new words emerge every day, leading to a great need for representing them with semantic meaning that is understandable to NLP systems. Sememes are defined as the mi…

cs.CL2018

SGM: Sequence Generation Model for Multi-label Classification

Pengcheng Yang, Xu Sun, Wei Li +3

Multi-label classification is an important yet challenging task in natural language processing. It is more complex than single-label classification in that the labels tend to be co…