Yoav Artzi

Publications
Influence

BERTScore: Evaluating Text Generation with BERT

Tianyi Zhang, V. Kishore, Felix Wu, Kilian Q. Weinberger, Yoav Artzi
Computer Science
ICLR
21 April 2019

We propose BERTScore, an automatic evaluation metric for text generation. Expand

Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies

Max Grusky, M. Naaman, Yoav Artzi
Computer Science
NAACL
30 April 2018

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

Scaling Semantic Parsers with On-the-Fly Ontology Matching

T. Kwiatkowski, Eunsol Choi, Yoav Artzi, Luke Zettlemoyer
Computer Science
EMNLP
1 October 2013

We introduce a new semantic parsing approach for scalable, open-domain ontological reasoning that learns to resolve ontological mismatches. Expand

Learning to Automatically Solve Algebra Word Problems

Nate Kushman, Luke Zettlemoyer, R. Barzilay, Yoav Artzi
Computer Science
ACL
1 June 2014

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

Training RNNs as Fast as CNNs

Tao Lei, Yu Zhang, Yoav Artzi
Computer Science
EMNLP
8 September 2017

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

A Corpus for Reasoning About Natural Language Grounded in Photographs

Alane Suhr, Stephanie Zhou, Iris Zhang, Huajun Bai, Yoav Artzi
Computer Science
ACL
1 November 2018

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

Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions

Yoav Artzi, Luke Zettlemoyer
Computer Science
Transactions of the Association for Computational…
31 March 2013

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

TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments

Howard Chen, Alane Suhr, Dipendra Kumar Misra, Noah Snavely, Yoav Artzi
Computer Science
IEEE/CVF Conference on Computer Vision and…
29 November 2018

We study the problem of jointly reasoning about language and vision through a navigation and spatial reasoning task. Expand

Simple Recurrent Units for Highly Parallelizable Recurrence

Tao Lei, Y. Zhang, Sida I. Wang, Huijing Dai, Yoav Artzi
Computer Science
EMNLP
8 September 2017

We propose the Simple Recurrent Unit (SRU), a light recurrent unit that balances model capacity and scalability. Expand

Broad-coverage CCG Semantic Parsing with AMR

Yoav Artzi, Kenton Lee, Luke Zettlemoyer
Computer Science
EMNLP
1 September 2015

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

Recommended Authors