Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT

Benjamin MullerYanai ElazarBenoît SagotDjamé Seddah
2021
EACL

Multilingual pretrained language models have demonstrated remarkable zero-shot crosslingual transfer capabilities. Such transfer emerges by fine-tuning on a task of interest in one language and… 

Evaluating the Evaluation of Diversity in Natural Language Generation

Guy TevetJonathan Berant
2021
EACL

Despite growing interest in natural language generation (NLG) models that produce diverse outputs, there is currently no principled method for evaluating the diversity of an NLG system. In this… 

BERTese: Learning to Speak to BERT

Adi HavivJonathan BerantA. Globerson
2021
EACL

Large pre-trained language models have been shown to encode large amounts of world and commonsense knowledge in their parameters, leading to substantial interest in methods for extracting that… 

Discourse Understanding and Factual Consistency in Abstractive Summarization

Saadia GabrielAntoine BosselutJeff DaYejin Choi
2021
EACL

We introduce Cooperative Generator-Discriminator Networks (Co-opNet), a general framework for abstractive summarization with distinct modeling of the narrative flow in the output summary. Most… 

Challenges in Algorithmic Debiasing for Toxic Language Detection

Xuhui ZhouMaarten SapSwabha SwayamdiptaYejin Choi
2021
EACL

Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently… 

Challenges in Automated Debiasing for Toxic Language Detection

Xuhui ZhouMaarten SapSwabha SwayamdiptaYejin Choi
2021
EACL

Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently… 

Misinfo Reaction Frames: Reasoning about Readers' Reactions to News Headlines (preprint)

Saadia GabrielSkyler HallinanMaarten SapYejin Choi
2021
ACL

Even to a simple and short news headline, readers react in a multitude of ways: cognitively (e.g., inferring the writer's intent), emotionally (e.g., feeling distrust), and behaviorally (e.g.,… 

CLIPScore: A Reference-free Evaluation Metric for Image Captioning

Jack HesselAri HoltzmanMaxwell ForbesYejin Choi
2021
EMNLP

Image captioning has conventionally relied on reference-based automatic evaluations, where machine captions are compared against captions written by humans. This is in contrast to the reference-free… 

GridToPix: Training Embodied Agents with Minimal Supervision

Unnat JainIou-Jen LiuS. LazebnikA. Schwing
2021
ICCV

While deep reinforcement learning (RL) promises freedom from hand-labeled data, great successes, especially for Embodied AI, require significant work to create supervision via carefully shaped… 

Contrasting Contrastive Self-Supervised Representation Learning Pipelines

Klemen KotarGabriel IlharcoLudwig SchmidtR. Mottaghi
2021
IEEE/CVF International Conference on Computer Vision (ICCV)

In the past few years, we have witnessed remarkable breakthroughs in self-supervised representation learning. Despite the success and adoption of representations learned through this paradigm, much…