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

MS2: Multi-Document Summarization of Medical Studies

Jay DeYoungIz BeltagyMadeleine van ZuylenLucy Lu Wang
2021
EMNLP

To assess the effectiveness of any medical intervention, researchers must conduct a timeintensive and highly manual literature review. NLP systems can help to automate or assist in parts of this… 

Achieving Model Robustness through Discrete Adversarial Training

Maor IvgiJonathan Berant
2021
EMNLP

Discrete adversarial attacks are symbolic perturbations to a language input that preserve the output label but lead to a prediction error. While such attacks have been extensively explored for the… 

What's in your Head? Emergent Behaviour in Multi-Task Transformer Models

Mor GevaUri KatzAviv Ben-ArieJonathan Berant
2021
EMNLP

The primary paradigm for multi-task training in natural language processing is to represent the input with a shared pre-trained language model, and add a small, thin network (head) per task. Given… 

Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences

Denis EmelinRonan Le BrasJena D. HwangYejin Choi
2021
EMNLP

In social settings, much of human behavior is governed by unspoken rules of conduct. For artificial systems to be fully integrated into social environments, adherence to such norms is a central… 

proScript: Partially Ordered Scripts Generation

Keisuke SakaguchiChandra BhagavatulaRonan Le BrasYejin Choi
2021
EMNLP • Findings

Scripts standardized event sequences describing typical everyday activities have been shown to help understand narratives by providing expectations, resolving ambiguity, and filling in unstated… 

Contrastive Explanations for Model Interpretability

Alon JacoviSwabha SwayamdiptaShauli RavfogelYoav Goldberg
2021
EMNLP

Contrastive explanations clarify why an event occurred in contrast to another. They are more inherently intuitive to humans to both produce and comprehend. We propose a methodology to produce… 

Back to Square One: Bias Detection, Training and Commonsense Disentanglement in the Winograd Schema

Yanai ElazarHongming ZhangYoav GoldbergDan Roth
2021
EMNLP

The Winograd Schema (WS) has been proposed as a test for measuring commonsense capabilities of models. Recently, pre-trained language model-based approaches have boosted performance on some WS… 

Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus

Jesse DodgeMaarten SapAna MarasovićMatt Gardner
2021
EMNLP

As language models are trained on ever more text, researchers are turning to some of the largest corpora available. Unlike most other types of datasets in NLP, large unlabeled text corpora are often… 

Generative Context Pair Selection for Multi-hop Question Answering

Dheeru DuaCicero Nogueira dos SantosPatrick NgSameer Singh
2021
EMNLP

Compositional reasoning tasks like multi-hop question answering, require making latent decisions to get the final answer, given a question. However, crowdsourced datasets often capture only a slice… 

Learning with Instance Bundles for Reading Comprehension

Dheeru DuaPradeep DasigiSameer Singh and Matt Gardner
2021
EMNLP

When training most modern reading comprehension models, all the questions associated with a context are treated as being independent from each other. However, closely related questions and their…