• Publications
  • Influence
Revealing the Dark Secrets of BERT
TLDR
We propose a methodology and offer the first detailed analysis of BERT’s capacity to capture different kinds of linguistic information in its self-attention weights. Expand
  • 158
  • 19
  • PDF
Lessons from Natural Language Inference in the Clinical Domain
TLDR
We introduce MedNLI - a dataset annotated by doctors, performing a natural language inference task (NLI), grounded in the medical history of patients. Expand
  • 69
  • 15
  • PDF
Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting
TLDR
We present a large-scale study of gender bias in occupation classification, a task where the use of machine learning may lead to negative outcomes on peoples' lives. Expand
  • 61
  • 6
  • PDF
RuSentiment: An Enriched Sentiment Analysis Dataset for Social Media in Russian
TLDR
This paper presents RuSentiment, a new dataset for sentiment analysis of social media posts in Russian, and a new set of comprehensive annotation guidelines that are extensible to other languages. Expand
  • 23
  • 6
  • PDF
GhostWriter: Using an LSTM for Automatic Rap Lyric Generation
TLDR
This paper demonstrates the effectiveness of a Long Short-Term Memory language model in our initial efforts to generate unconstrained rap lyrics: this is the task of ghostwriting. Expand
  • 70
  • 5
  • PDF
SemEval-2017 Task 6: #HashtagWars: Learning a Sense of Humor
TLDR
This paper describes a new shared task for humor understanding that attempts to eschew the ubiquitous binary approach to humor detection and focus on comparative humor ranking instead. Expand
  • 41
  • 5
  • PDF
Here's My Point: Joint Pointer Architecture for Argument Mining
TLDR
We propose a novel architecture that applies Pointer Network sequence-to-sequence attention modeling to structural prediction in discourse parsing tasks. Expand
  • 33
  • 5
  • PDF
What's in a Name? Reducing Bias in Bios without Access to Protected Attributes
TLDR
In the context of mitigating bias in occupation classification, we propose a method for discouraging correlation between the predicted probability of an individual's true occupation and a word embedding of their name. Expand
  • 25
  • 4
  • PDF
Adversarial Decomposition of Text Representation
TLDR
In this paper, we present a method for adversarial decomposition of text representation. Expand
  • 22
  • 3
  • PDF
Combining Network and Language Indicators for Tracking Conflict Intensity
TLDR
This work seeks to analyze the dynamics of social or political conflict as it develops over time, using a combination of network-based and language-based measures of conflict intensity derived from social media data. Expand
  • 6
  • 3
  • PDF
...
1
2
3
4
...