• Publications
  • Influence
Teaching Machines to Read and Comprehend
TLDR
We develop a class of attention based deep neural networks that learn to read real documents and answer complex questions with minimal prior knowledge of language structure. Expand
  • 1,716
  • 291
  • PDF
Reasoning about Entailment with Neural Attention
TLDR
In this paper, we propose a neural model that reads two sentences to determine entailment using long short-term memory units. Expand
  • 576
  • 82
  • PDF
The NarrativeQA Reading Comprehension Challenge
TLDR
We present a new dataset and set of tasks in which the reader must answer questions about stories by reading entire books or movie scripts. Expand
  • 205
  • 52
  • PDF
Latent Predictor Networks for Code Generation
TLDR
We present a novel neural network architecture which generates an output sequence conditioned on an arbitrary number of input functions. Expand
  • 202
  • 26
  • PDF
Optimizing Performance of Recurrent Neural Networks on GPUs
TLDR
In this article we demonstrate that by exposing parallelism between operations within the network, an order of magnitude speedup across a range of network sizes can be achieved over a naive implementation. Expand
  • 65
  • 13
  • PDF
Semantic Parsing with Semi-Supervised Sequential Autoencoders
TLDR
We present a novel semi-supervised approach for sequence transduction and apply it to semantic parsing and extend those datasets with synthetically generated logical forms. Expand
  • 64
  • 7
  • PDF
Learning Bilingual Word Representations by Marginalizing Alignments
TLDR
We present a probabilistic model that simultaneously learns alignments and distributed representations for bilingual data. Expand
  • 81
  • 5
  • PDF
Learning and Evaluating General Linguistic Intelligence
TLDR
We define general linguistic intelligence as the ability to reuse previously acquired knowledge about a language's lexicon, syntax, semantics, and pragmatic conventions to adapt to new tasks. Expand
  • 70
  • 4
  • PDF
The Neural Noisy Channel
TLDR
We formulate sequence to sequence transduction as a noisy channel decoding problem and use recurrent neural networks to parameterise the source and channel models to obtain a tractable and effective beam search decoder. Expand
  • 42
  • 3
  • PDF
Aggregation and Ordering in Factorised Databases
TLDR
In this paper, we extend FDB to support a larger class of practical queries with aggregates and ordering, while still maintaining its performance superiority over relational query techniques. Expand
  • 53
  • 2
  • PDF