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

Universal Adversarial Triggers for Attacking and Analyzing NLP

Eric WallaceShi FengNikhil KandpalSameer Singh
2019
EMNLP

dversarial examples highlight model vulnerabilities and are useful for evaluation and interpretation. We define universal adversarial triggers: input-agnostic sequences of tokens that trigger a… 

Y'all should read this! Identifying Plurality in Second-Person Personal Pronouns in English Texts

Gabriel StanovskyRonen Tamari
2019
EMNLP • W-NUT

Distinguishing between singular and plural "you" in English is a challenging task which has potential for downstream applications, such as machine translation or coreference resolution. While formal… 

Compositional Questions Do Not Necessitate Multi-hop Reasoning

Sewon MinEric WallaceSameer SinghLuke Zettlemoyer
2019
ACL

Multi-hop reading comprehension (RC) questions are challenging because they require reading and reasoning over multiple paragraphs. We argue that it can be difficult to construct large multi-hop RC… 

GrapAL: Connecting the Dots in Scientific Literature

Christine BettsJoanna PowerWaleed Ammar
2019
ACL

We introduce GrapAL (Graph database of Academic Literature), a versatile tool for exploring and investigating a knowledge base of scientific literature, that was semi-automatically constructed using… 

The Risk of Racial Bias in Hate Speech Detection

Maarten SapDallas CardSaadia GabrielNoah A. Smith
2019
ACL

We investigate how annotators’ insensitivity to differences in dialect can lead to racial bias in automatic hate speech detection models, potentially amplifying harm against minority populations. We… 

Question Answering is a Format; When is it Useful?

Matt GardnerJonathan BerantHannaneh HajishirziSewon Min
2019
arXiv

Recent years have seen a dramatic expansion of tasks and datasets posed as question answering, from reading comprehension, semantic role labeling, and even machine translation, to image and video… 

Robust Navigation with Language Pretraining and Stochastic Sampling

Xiujun LiChunyuan LiQiaolin XiaYejin Choi
2019
EMNLP

Core to the vision-and-language navigation (VLN) challenge is building robust instruction representations and action decoding schemes, which can generalize well to previously unseen instructions and… 

Shallow Syntax in Deep Water

Swabha SwayamdiptaMatthew E. PetersBrendan RoofNoah A. Smith
2019
arXiv

Shallow syntax provides an approximation of phrase-syntactic structure of sentences; it can be produced with high accuracy, and is computationally cheap to obtain. We investigate the role of shallow… 

To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks

Matthew E. PetersSebastian RuderNoah A. Smith
2019
ACL • RepL4NLP

While most previous work has focused on different pretraining objectives and architectures for transfer learning, we ask how to best adapt the pretrained model to a given target task. We focus on… 

Evaluating Gender Bias in Machine Translation

Gabriel StanovskyNoah A. SmithLuke Zettlemoyer
2019
ACL

We present the first challenge set and evaluation protocol for the analysis of gender bias in machine translation (MT). Our approach uses two recent coreference resolution datasets composed of…