• Publications
  • Influence
NewsQA: A Machine Comprehension Dataset
TLDR
We present NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs and compare it to several strong neural models. Expand
  • 387
  • 92
  • PDF
TextWorld: A Learning Environment for Text-based Games
TLDR
We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. Expand
  • 97
  • 23
  • PDF
Machine Comprehension by Text-to-Text Neural Question Generation
TLDR
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. Expand
  • 110
  • 11
  • PDF
A Joint Model for Question Answering and Question Generation
TLDR
We propose a generative machine comprehension model that learns jointly to ask and answer questions based on documents. Expand
  • 62
  • 10
  • PDF
Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension
TLDR
We propose a neural machine-reading model that constructs dynamic knowledge graphs from procedural text, and use them to track the evolving states of participant entities. Expand
  • 50
  • 9
  • PDF
Neural Models for Key Phrase Detection and Question Generation
TLDR
We propose a two-stage neural model to tackle question generation from documents. Expand
  • 58
  • 8
  • PDF
One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases
Different texts shall by nature correspond to different number of keyphrases. This desideratum is largely missing from existing neural keyphrase generation models. In this study, we address thisExpand
  • 15
  • 8
  • PDF
Generating Diverse Numbers of Diverse Keyphrases
TLDR
We propose a recurrent generative model that generates multiple keyphrases sequentially from a text, with specific modules that promote generation diversity. Expand
  • 14
  • 7
  • PDF
A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data
TLDR
We present a parallel-hierarchical approach to machine comprehension designed to work well in a data-limited setting. Expand
  • 40
  • 6
  • PDF
Counting to Explore and Generalize in Text-based Games
TLDR
We propose a recurrent RL agent with an episodic exploration mechanism that helps discovering good policies in text-based game environments. Expand
  • 29
  • 6
  • PDF
...
1
2
3
...