activity
20182021
most citedDynamically Fused Graph Network for Multi-hop Reasoning

43 citations · 74 across the 4 of their papers we have counts for

collaborators

12 papers

cs.LG20218 cited

Task-wise Split Gradient Boosting Trees for Multi-center Diabetes Prediction

Mingcheng Chen, Zhenghui Wang, Zhiyun Zhao +14

Diabetes prediction is an important data science application in the social healthcare domain. There exist two main challenges in the diabetes prediction task: data heterogeneity si…

cs.CL2020

A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation

Dinghan Shen, Mingzhi Zheng, Yelong Shen +2

Adversarial training has been shown effective at endowing the learned representations with stronger generalization ability. However, it typically requires expensive computation to…

cs.CL2020

CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding

Yanru Qu, Dinghan Shen, Yelong Shen +3

Data augmentation has been demonstrated as an effective strategy for improving model generalization and data efficiency. However, due to the discrete nature of natural language, de…

cs.CL20206 cited

Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning

Yuning Mao, Yanru Qu, Yiqing Xie +2

While neural sequence learning methods have made significant progress in single-document summarization (SDS), they produce unsatisfactory results on multi-document summarization (M…

cs.AI202017 cited

GIKT: A Graph-based Interaction Model for Knowledge Tracing

Yang Yang, Jian Shen, Yanru Qu +5

With the rapid development in online education, knowledge tracing (KT) has become a fundamental problem which traces students' knowledge status and predicts their performance on ne…

cs.IR2019

An End-to-End Neighborhood-based Interaction Model for Knowledge-enhanced Recommendation

Yanru Qu, Ting Bai, Weinan Zhang +2

This paper studies graph-based recommendation, where an interaction graph is constructed from historical records and is lever-aged to alleviate data sparsity and cold start problem…