activity
20152023
most citedUniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training

225 citations · 2.1k across the 54 of their papers we have counts for

collaborators
Showing 2017Show all

16 papers · 1 filter

cs.CL2017

Stochastic Answer Networks for Machine Reading Comprehension

Xiaodong Liu, Yelong Shen, Kevin Duh +1

We propose a simple yet robust stochastic answer network (SAN) that simulates multi-step reasoning in machine reading comprehension. Compared to previous work such as ReasoNet whic…

cs.RO2017

CPG-Based Control Scheme for Quadruped Robot to Withstand the Lateral Impact

Qingsheng Luo, Chenyang Zhou, Yan Jia +2

This paper aims to present a stability control strategy for quadruped robot under lateral impact with the help of lateral trot. We firstly propose five necessary conditions for kee…

cs.AI2017★ 14 cited

BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems

Zachary Lipton, Xiujun Li, Jianfeng Gao +3

We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawi…

cs.CL2017★ 1 cited

An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks

Yelong Shen, Xiaodong Liu, Kevin Duh +1

Reading comprehension (RC) is a challenging task that requires synthesis of information across sentences and multiple turns of reasoning. Using a state-of-the-art RC model, we empi…

cs.CV2017

Language-Based Image Editing with Recurrent Attentive Models

Jianbo Chen, Yelong Shen, Jianfeng Gao +2

We investigate the problem of Language-Based Image Editing (LBIE). Given a source image and a natural language description, we want to generate a target image by editing the source…

cs.CL2017

Dynamic Fusion Networks for Machine Reading Comprehension

Yichong Xu, Jingjing Liu, Jianfeng Gao +2

This paper presents a novel neural model - Dynamic Fusion Network (DFN), for machine reading comprehension (MRC). DFNs differ from most state-of-the-art models in their use of a dy…