activity
20172025
most citedConnecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks

117 citations · 411 across the 24 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2022

Perceiving the World: Question-guided Reinforcement Learning for Text-based Games

Yunqiu Xu, Meng Fang, Ling Chen +3

Text-based games provide an interactive way to study natural language processing. While deep reinforcement learning has shown effectiveness in developing the game playing agent, th…

cs.CL2021

Generalization in Text-based Games via Hierarchical Reinforcement Learning

Yunqiu Xu, Meng Fang, Ling Chen +2

Deep reinforcement learning provides a promising approach for text-based games in studying natural language communication between humans and artificial agents. However, the general…

cs.CL20203 cited

Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention

Yang Li, Tao Shen, Guodong Long +3

Wrong labeling problem and long-tail relations are two main challenges caused by distant supervision in relation extraction. Recent works alleviate the wrong labeling by selective…

cs.CL2020

RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion

Hao Huang, Guodong Long, Tao Shen +2

Many graph embedding approaches have been proposed for knowledge graph completion via link prediction. Among those, translating embedding approaches enjoy the advantages of light-w…

cs.CL2018

Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together

Tao Shen, Tianyi Zhou, Guodong Long +2

Neural networks equipped with self-attention have parallelizable computation, light-weight structure, and the ability to capture both long-range and local dependencies. Further, th…

cs.CL2018

Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling

Tao Shen, Tianyi Zhou, Guodong Long +2

Recurrent neural networks (RNN), convolutional neural networks (CNN) and self-attention networks (SAN) are commonly used to produce context-aware representations. RNN can capture l…