• Publications
  • Influence
BERTScore: Evaluating Text Generation with BERT
TLDR
We propose BERTScore, an automatic evaluation metric for text generation. Expand
  • 365
  • 122
  • PDF
Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies
TLDR
We present NEWSROOM, a summarization dataset of 1.3 million articles and summaries written by authors and editors in newsrooms of 38 major news publications. Expand
  • 165
  • 48
  • PDF
Scaling Semantic Parsers with On-the-Fly Ontology Matching
TLDR
We introduce a new semantic parsing approach for scalable, open-domain ontological reasoning that learns to resolve ontological mismatches. Expand
  • 290
  • 37
  • PDF
Learning to Automatically Solve Algebra Word Problems
TLDR
We present an approach for automatically learning to solve algebra word problems, demonstrating that the system can correctly answer almost 70% of the questions in the dataset. Expand
  • 192
  • 37
  • PDF
Training RNNs as Fast as CNNs
TLDR
We propose the Simple Recurrent Unit (SRU) architecture, a recurrent module that runs as fast as CNNs and scales easily to over 10 layers. Expand
  • 136
  • 34
  • PDF
A Corpus for Reasoning About Natural Language Grounded in Photographs
TLDR
We introduce a new dataset for joint reasoning about natural language and images, with a focus on semantic diversity, compositionality, and visual reasoning challenges. Expand
  • 105
  • 32
  • PDF
Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions
TLDR
We introduce a grounded CCG semantic parsing approach that learns a joint model of meaning and context for interpreting and executing natural language instructions, using various types of weak supervision. Expand
  • 372
  • 29
  • PDF
TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments
TLDR
We study the problem of jointly reasoning about language and vision through a navigation and spatial reasoning task. Expand
  • 115
  • 28
  • PDF
Simple Recurrent Units for Highly Parallelizable Recurrence
TLDR
We propose the Simple Recurrent Unit (SRU), a light recurrent unit that balances model capacity and scalability. Expand
  • 131
  • 20
  • PDF
Broad-coverage CCG Semantic Parsing with AMR
TLDR
We present a new model that combines CCG parsing to recover compositional aspects of meaning and a factor graph to model non-compositional phenomena, such as anaphoric dependencies. Expand
  • 135
  • 17
  • PDF
...
1
2
3
4
5
...