2.2k citations · 10.9k across the 144 of their papers we have counts for
7 papers · 1 filter
Robust Conversational AI with Grounded Text Generation
Jianfeng Gao, Baolin Peng, Chunyuan Li +4
This article presents a hybrid approach based on a Grounded Text Generation (GTG) model to building robust task bots at scale. GTG is a hybrid model which uses a large-scale Transf…
M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search
Yelong Shen, Jianshu Chen, Po-Sen Huang +2
Learning to walk over a graph towards a target node for a given query and a source node is an important problem in applications such as knowledge base completion (KBC). It can be f…
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…
Link Prediction using Embedded Knowledge Graphs
Yelong Shen, Po-Sen Huang, Ming-Wei Chang +1
Since large knowledge bases are typically incomplete, missing facts need to be inferred from observed facts in a task called knowledge base completion. The most successful approach…
Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks
Yun-Nung Chen, Dilek Hakkani-Tur, Gokhan Tur +3
Natural language understanding (NLU) is a core component of a spoken dialogue system. Recently recurrent neural networks (RNN) obtained strong results on NLU due to their superior…
Basic Reasoning with Tensor Product Representations
Paul Smolensky, Moontae Lee, Xiaodong He +3
In this paper we present the initial development of a general theory for mapping inference in predicate logic to computation over Tensor Product Representations (TPRs; Smolensky (1…
Deep Reinforcement Learning with a Natural Language Action Space
Ji He, Jianshu Chen, Xiaodong He +4
This paper introduces a novel architecture for reinforcement learning with deep neural networks designed to handle state and action spaces characterized by natural language, as fou…