• Publications
  • Influence
A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification
TLDR
Convolutional Neural Networks (CNNs) have recently achieved remarkably strong performance on the practically important task of sentence classification. Expand
  • 624
  • 67
  • PDF
Closing the Gap between Methodologists and End-Users: R as a Computational Back-End
TLDR
We present a framework that allows methodologists to implement new methods in R that are then automatically integrated into the GUI for use by end-users, so long as the programmer conforms to our interface. Expand
  • 516
  • 41
Semi-automated screening of biomedical citations for systematic reviews
TLDR
We present a novel online classification strategy for citation screening to automatically discriminate "relevant" from "irrelevant" citations, without excluding any of the citations eligible for the systematic review. Expand
  • 213
  • 21
Attention is not Explanation
TLDR
We empirically investigate the relationship between attention weights, inputs, and outputs in neural NLP models. Expand
  • 258
  • 21
  • PDF
Modelling Context with User Embeddings for Sarcasm Detection in Social Media
TLDR
We introduce a deep neural network for automated sarcasm detection on social media that does not require extensive feature engineering. Expand
  • 122
  • 19
  • PDF
Meta-Analyst: software for meta-analysis of binary, continuous and diagnostic data
TLDR
We have developed and validated a new program for conducting meta-analyses that combines the advantages of existing software for this task. Meta-Analyst is implemented in C# atop of the Microsoft .NET framework. Expand
  • 429
  • 17
  • PDF
Deploying an interactive machine learning system in an evidence-based practice center: abstrackr
TLDR
We develop abstrackr, an online tool for the task of citation screening for systematic reviews. Expand
  • 229
  • 16
  • PDF
ERASER: A Benchmark to Evaluate Rationalized NLP Models
TLDR
We propose the Evaluating Rationales And Simple English Reasoning (ERASER) benchmark to advance research on interpretable models in NLP that reveal the `reasoning' behind model outputs. Expand
  • 50
  • 14
  • PDF
A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature
TLDR
We present a corpus of 5,000 richly annotated abstracts of medical articles describing clinical randomized controlled trials. Expand
  • 52
  • 11
  • PDF
Aggregating and Predicting Sequence Labels from Crowd Annotations
TLDR
We propose a novel Hidden Markov Model variant of Long Short Term Memory that can predict sequences in unannotated text. Expand
  • 36
  • 11
  • PDF