• Publications
  • Influence
SQuAD: 100, 000+ Questions for Machine Comprehension of Text
tl;dr
We present the Stanford Question Answering Dataset (SQuAD), a new reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage. Expand
  • 2,118
  • 617
  • Open Access
Generating News Headlines with Recurrent Neural Networks
tl;dr
We describe an application of an encoder-decoder recurrent neural network with LSTM units and attention to generating headlines from the text of news articles. Expand
  • 68
  • 5
  • Open Access
Learning Distributed Representations of Phrases
tl;dr
In this project I focus my attention on learning representations of phrases - sequences of two or more words that can function as a single unit in sentence. Expand
  • 2
  • Open Access
Spectral Clustering of Wikipedia Articles Using the Edit History
The spectral clustering algorithm is a powerful clustering algorithm that is known to give better clusterings than other algorithms such as k-means. Most spectral clustering scenarios require theExpand