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

RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models

Samuel GehmanSuchin GururanganMaarten SapNoah A. Smith
2020
Findings of EMNLP

Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs can… 

The Multilingual Amazon Reviews Corpus

Phillip KeungY. LuGyorgy SzarvasNoah A. Smith
2020
EMNLP

We present the Multilingual Amazon Reviews Corpus (MARC), a large-scale collection of Amazon reviews for multilingual text classification. The corpus contains reviews in English, Japanese, German,… 

TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions

Qiang NingHao WuRujun HanDan Roth
2020
EMNLP

A critical part of reading is being able to understand the temporal relationships between events described in a passage of text, even when those relationships are not explicitly stated. However,… 

Writing Strategies for Science Communication: Data and Computational Analysis

Tal AugustLauren KimKatharina ReineckeNoah A. Smith
2020
EMNLP

Communicating complex scientific ideas without misleading or overwhelming the public is challenging. While science communication guides exist, they rarely offer empirical evidence for how their… 

Evaluating Models' Local Decision Boundaries via Contrast Sets

M. GardnerY. ArtziV. Basmovaet al
2020
Findings of EMNLP

Standard test sets for supervised learning evaluate in-distribution generalization. Unfortunately, when a dataset has systematic gaps (e.g., annotation artifacts), these evaluations are misleading:… 

Break It Down: A Question Understanding Benchmark

Tomer WolfsonMor GevaAnkit GuptaJonathan Berant
2020
TACL

Understanding natural language questions entails the ability to break down a question into the requisite steps for computing its answer. In this work, we introduce a Question Decomposition Meaning… 

CORD-19: The Covid-19 Open Research Dataset

L. Lu WangK. LoY. ChandrasekharS. Kohlmeier
2020
ACL • NLP-COVID

The Covid-19 Open Research Dataset (CORD-19) is a growing 1 resource of scientific papers on Covid-19 and related historical coronavirus research. CORD-19 is designed to facilitate the development… 

A Formal Hierarchy of RNN Architectures

William. MerrillGail Garfinkel WeissYoav GoldbergEran Yahav
2020
ACL

We develop a formal hierarchy of the expressive capacity of RNN architectures. The hierarchy is based on two formal properties: space complexity, which measures the RNN's memory, and rational… 

A Mixture of h-1 Heads is Better than h Heads

Hao PengRoy SchwartzDianqi LiNoah A. Smith
2020
ACL

Multi-head attentive neural architectures have achieved state-of-the-art results on a variety of natural language processing tasks. Evidence has shown that they are overparameterized; attention… 

Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks

Suchin GururanganAna MarasovićSwabha SwayamdiptaNoah A. Smith
2020
ACL

Language models pretrained on text from a wide variety of sources form the foundation of today's NLP. In light of the success of these broad-coverage models, we investigate whether it is still…