• Publications
  • Influence
DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
TLDR
We study the problem of learning to reason in large scale knowledge graphs (KGs). Expand
  • 176
  • 42
  • PDF
"Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection
TLDR
In this paper, we present liar: a new, publicly available dataset for fake news detection. Expand
  • 389
  • 39
  • PDF
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
TLDR
We propose a novel Reinforced Cross-Modal Matching (RCM) approach that enforces cross-modal grounding both locally and globally via reinforcement learning (RL). Expand
  • 114
  • 23
  • PDF
KBGAN: Adversarial Learning for Knowledge Graph Embeddings
TLDR
We introduce KBGAN, an adversarial learning framework to improve the performances of a wide range of existing knowledge graph embedding models. Expand
  • 98
  • 17
  • PDF
No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling
TLDR
We propose an Adversarial REward Learning (AREL) framework to learn an implicit reward function from human demonstrations and then optimize policy search with the learned reward function. Expand
  • 70
  • 17
  • PDF
Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
TLDR
We exploit the structure of dialog acts to build a multi-layer hierarchical graph, where each act is represented as a root-to-leaf route on the graph. Expand
  • 43
  • 16
  • PDF
Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning
TLDR
In this paper, we investigate the possibility of using dynamic selection strategies for robust distant supervision. Expand
  • 93
  • 13
  • PDF
Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation
TLDR
We propose a novel, planned-ahead hybrid reinforcement learning model that combines model-free and model-based reinforcement learning to solve a real-world vision-language navigation task. Expand
  • 70
  • 13
  • PDF
One-Shot Relational Learning for Knowledge Graphs
TLDR
We propose a one-shot relational learning framework that utilizes the knowledge distilled by embedding models and learns a matching metric by considering both the learned embeddings and one-hop graph structures. Expand
  • 43
  • 12
  • PDF
VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research
TLDR
We present a new large-scale multilingual video description dataset, VATEX, which contains over 41,250 videos and 825,000 captions in both English and Chinese. Expand
  • 43
  • 11
  • PDF