Yoav Artzi

Revisiting Few-sample BERT Fine-tuning

We study the problem of few-sample fine-tuning of BERT contextual repres...
06/10/2020 ∙ by Tianyi Zhang, et al. ∙ 0 ∙ share

read it
What is Learned in Visually Grounded Neural Syntax Acquisition

Visual features are a promising signal for learning bootstrap textual mo...
05/04/2020 ∙ by Noriyuki Kojima, et al. ∙ 0 ∙ share

read it
Evaluating NLP Models via Contrast Sets

Standard test sets for supervised learning evaluate in-distribution gene...
04/06/2020 ∙ by Matt Gardner, et al. ∙ 0 ∙ share

read it
Retouchdown: Adding Touchdown to StreetLearn as a Shareable Resource for Language Grounding Tasks in Street View

The Touchdown dataset (Chen et al., 2019) provides instructions by human...
01/10/2020 ∙ by Harsh Mehta, et al. ∙ 9 ∙ share

read it
Interactive Classification by Asking Informative Questions

Natural language systems often rely on a single, potentially ambiguous i...
11/09/2019 ∙ by Lili Yu, et al. ∙ 0 ∙ share

read it
Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight

We propose a joint simulation and real-world learning framework for mapp...
10/21/2019 ∙ by Valts Blukis, et al. ∙ 21 ∙ share

read it
Executing Instructions in Situated Collaborative Interactions

We study a collaborative scenario where a user not only instructs a syst...
10/08/2019 ∙ by Alane Suhr, et al. ∙ 11 ∙ share

read it
NLVR2 Visual Bias Analysis

NLVR2 (Suhr et al., 2019) was designed to be robust for language bias th...
09/23/2019 ∙ by Alane Suhr, et al. ∙ 0 ∙ share

read it
BERTScore: Evaluating Text Generation with BERT

We propose BERTScore, an automatic evaluation metric for text generation...
04/21/2019 ∙ by Tianyi Zhang, et al. ∙ 0 ∙ share

read it
Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments

We study the problem of jointly reasoning about language and vision thro...
11/29/2018 ∙ by Howard Chen, et al. ∙ 10 ∙ share

read it
Early Fusion for Goal Directed Robotic Vision

Increasingly, perceptual systems are being codified as strict pipelines ...
11/21/2018 ∙ by Aaron Walsman, et al. ∙ 10 ∙ share

read it
Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction

We propose an approach for mapping natural language instructions and raw...
11/10/2018 ∙ by Valts Blukis, et al. ∙ 0 ∙ share

read it
A Corpus for Reasoning About Natural Language Grounded in Photographs

We introduce a new dataset for joint reasoning about language and vision...
11/01/2018 ∙ by Alane Suhr, et al. ∙ 2 ∙ share

read it
Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction

We propose to decompose instruction execution to goal prediction and act...
09/04/2018 ∙ by Dipendra Misra, et al. ∙ 0 ∙ share

read it
Following High-level Navigation Instructions on a Simulated Quadcopter with Imitation Learning

We introduce a method for following high-level navigation instructions b...
05/31/2018 ∙ by Valts Blukis, et al. ∙ 0 ∙ share

read it
Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation

We propose a learning approach for mapping context-dependent sequential ...
05/25/2018 ∙ by Alane Suhr, et al. ∙ 0 ∙ share

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

We present NEWSROOM, a summarization dataset of 1.3 million articles and...
04/30/2018 ∙ by Max Grusky, et al. ∙ 0 ∙ share

read it
Learning to Map Context-Dependent Sentences to Executable Formal Queries

We propose a context-dependent model to map utterances within an interac...
04/18/2018 ∙ by Alane Suhr, et al. ∙ 0 ∙ share

read it
CHALET: Cornell House Agent Learning Environment

We present CHALET, a 3D house simulator with support for navigation and ...
01/23/2018 ∙ by Claudia Yan, et al. ∙ 0 ∙ share

read it
Visual Reasoning with Natural Language

Natural language provides a widely accessible and expressive interface f...
10/02/2017 ∙ by Stephanie Zhou, et al. ∙ 0 ∙ share

read it
Training RNNs as Fast as CNNs

Common recurrent neural network architectures scale poorly due to the in...
09/08/2017 ∙ by Tao Lei, et al. ∙ 0 ∙ share

read it
Mapping Instructions and Visual Observations to Actions with Reinforcement Learning

We propose to directly map raw visual observations and text input to act...
04/28/2017 ∙ by Dipendra Misra, et al. ∙ 0 ∙ share

read it

Yoav Artzi

Featured Co-authors

Yu Zhang

Noah A. Smith

Dieter Fox

Yejin Choi

Jonathan Berant

Alexander M. Rush

Kilian Q. Weinberger

John Langford

Sameer Singh

Noah Snavely

Matt Gardner

Revisiting Few-sample BERT Fine-tuning

What is Learned in Visually Grounded Neural Syntax Acquisition

Evaluating NLP Models via Contrast Sets

Retouchdown: Adding Touchdown to StreetLearn as a Shareable Resource for Language Grounding Tasks in Street View

Interactive Classification by Asking Informative Questions

Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight

Executing Instructions in Situated Collaborative Interactions

NLVR2 Visual Bias Analysis

BERTScore: Evaluating Text Generation with BERT

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

Early Fusion for Goal Directed Robotic Vision

Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction

A Corpus for Reasoning About Natural Language Grounded in Photographs

Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction

Following High-level Navigation Instructions on a Simulated Quadcopter with Imitation Learning

Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation

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

Learning to Map Context-Dependent Sentences to Executable Formal Queries

CHALET: Cornell House Agent Learning Environment

Visual Reasoning with Natural Language

Training RNNs as Fast as CNNs

Mapping Instructions and Visual Observations to Actions with Reinforcement Learning