• Publications
  • Influence
Character-Aware Neural Language Models
TLDR
We describe a simple neural language model that relies only on character-level inputs. Expand
  • 1,301
  • 155
  • PDF
Discourse-Based Objectives for Fast Unsupervised Sentence Representation Learning
TLDR
We introduce a novel objective function for the unsupervised training of neural network sentence encoders. Expand
  • 70
  • 9
  • PDF
ELI5: Long Form Question Answering
TLDR
We introduce the first large-scale corpus for long form question answering, a task requiring elaborate and in-depth answers to open-ended questions that require explanations. Expand
  • 47
  • 7
  • PDF
Variable Computation in Recurrent Neural Networks
TLDR
In this paper, we explore a modification to existing recurrent units which allows them to learn to vary the amount of computation they perform at each step, without prior knowledge of the sequence's time structure. Expand
  • 39
  • 6
  • PDF
Creating an automated trigger for sepsis clinical decision support at emergency department triage using machine learning
Objective To demonstrate the incremental benefit of using free text data in addition to vital sign and demographic data to identify patients with suspected infection in the emergency department.Expand
  • 116
  • 5
  • PDF
KILT: a Benchmark for Knowledge Intensive Language Tasks
Challenging problems such as open-domain question answering, fact checking, slot filling and entity linking require access to large, external knowledge sources. While some models do well onExpand
  • 29
  • 3
  • PDF
Grounded Recurrent Neural Networks
TLDR
In this work, we present the Grounded Recurrent Neural Network (GRNN), a recurrent neural network architecture for multi-label prediction which explicitly ties labels to specific dimensions of the recurrent hidden state (we call this process "grounding"). Expand
  • 16
  • 3
  • PDF
Predicting Chief Complaints at Triage Time in the Emergency Department
As hospitals increasingly use electronic medical records for research and quality improvement, it is important to provide ways to structure medical data without losing either expressiveness or time.Expand
  • 16
  • 3
  • PDF
Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation
TLDR
We provide a novel algorithm to simultaneously perform representation learning for input data and learning of the hierarchical predictor. Expand
  • 22
  • 2
  • PDF
Discovering Hidden Variables in Noisy-Or Networks using Quartet Tests
TLDR
We give a polynomial-time algorithm for provably learning the structure and parameters of bipartite noisy-or Bayesian networks of binary variables where the top layer is completely hidden. Expand
  • 22
  • 1
  • PDF
...
1
2
3
...