• Publications
  • Influence
A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories
TLDR
This paper introduces a new corpus of 50k five-sentence commonsense stories that captures a rich set of causal and temporal commonsense relations between daily events. Expand
  • 209
  • 49
  • PDF
Exploring Content Models for Multi-Document Summarization
TLDR
We present an exploration of generative probabilistic models for multi-document summarization. Expand
  • 365
  • 36
  • PDF
The Impact of Frequency on Summarization
TLDR
We describe SumBasic, a summarization system that exploits frequency exclusively to create summaries. Expand
  • 251
  • 33
  • PDF
Visual Storytelling
TLDR
We introduce the first dataset for sequential vision-to-language, and explore how this data may be used for the task of visual storytelling. Expand
  • 198
  • 27
  • PDF
Using Contextual Speller Techniques and Language Modeling for ESL Error Correction
TLDR
We present a modular system for detection and correction of errors made by nonnative (English as a Second Language = ESL) writers. Expand
  • 153
  • 20
  • PDF
Beyond SumBasic: Task-focused summarization with sentence simplification and lexical expansion
TLDR
We evaluate our results on two large datasets commonly used to evaluate task-focused summarization, the DUC2005 and DUC2006 datasets, using automatic metrics. Expand
  • 249
  • 19
  • PDF
A compositional context sensitive multi-document summarizer: exploring the factors that influence summarization
TLDR
A frequency based summarizer can achieve performance comparable to that of state-of-the-art systems, but only with a good composition function; context sensitivity improves performance and significantly reduces repetition. Expand
  • 228
  • 19
  • PDF
Generating Natural Questions About an Image
TLDR
In this paper, we introduce the novel task of Visual Question Generation (VQG), where the system is tasked with asking a natural and engaging question when shown an image. Expand
  • 180
  • 19
  • PDF
A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories
TLDR
This paper introduces a new corpus of ~50k five-sentence commonsense stories, ROCStories, to enable this evaluation. Expand
  • 93
  • 18
  • PDF
Powergrading: a Clustering Approach to Amplify Human Effort for Short Answer Grading
TLDR
We introduce a new approach to the machine-assisted grading of short answer questions. Expand
  • 97
  • 15
  • PDF