• Publications
  • Influence
Improving Language Understanding by Generative Pre-Training
TLDR
We use generative pre-training of a language model on a diverse corpus of unlabeled text, followed by discriminative fine-tuning on each specific task to improve upon the state of the art in 9 out of the 12 tasks studied. Expand
  • 2,005
  • 397
  • PDF
Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
TLDR
We present hierarchical-DQN, a framework to integrate hierarchical value functions, operating at different temporal scales, with intrinsically motivated deep reinforcement learning. Expand
  • 617
  • 52
  • PDF
Language Understanding for Text-based Games using Deep Reinforcement Learning
TLDR
We employ a deep reinforcement learning framework to jointly learn state representations and action policies for text-based strategy games using game rewards as feedback. Expand
  • 232
  • 33
  • PDF
Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge
TLDR
This paper explores the task of translating natural language queries into regular expressions which embody their meaning. Expand
  • 50
  • 14
  • PDF
Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
TLDR
We explore the task of acquiring and incorporating external evidence to improve extraction accuracy in domains where the amount of training data is scarce. Expand
  • 114
  • 12
  • PDF
An Unsupervised Method for Uncovering Morphological Chains
TLDR
We model word formation in terms of morphological chains, from base words to the observed words, breaking the chains into parent-child relations. Expand
  • 55
  • 11
  • PDF
Nonparametric Spherical Topic Modeling with Word Embeddings
TLDR
We use a Hierarchical Dirichlet Process for our base topic model and propose an efficient inference algorithm based on Stochastic Variational Inference. Expand
  • 57
  • 5
  • PDF
A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation
TLDR
We introduce a new algorithm for multi-objective reinforcement learning (MORL) with linear preferences, with the goal of enabling few-shot adaptation to new tasks. Expand
  • 26
  • 5
  • PDF
Machine Comprehension with Discourse Relations
TLDR
This paper proposes a novel approach for incorporating discourse information into machine comprehension applications. Expand
  • 50
  • 4
  • PDF
Representation Learning for Grounded Spatial Reasoning
TLDR
The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment. Expand
  • 34
  • 3
  • PDF
...
1
2
3
4
5
...