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

IIRC: A Dataset of Incomplete Information Reading Comprehension Questions

James FergusonMatt Gardner. Hannaneh HajishirziTushar KhotPradeep Dasigi
2020
EMNLP

Humans often have to read multiple documents to address their information needs. However, most existing reading comprehension (RC) tasks only focus on questions for which the contexts provide all… 

Improving Compositional Generalization in Semantic Parsing

Inbar OrenJonathan HerzigNitish GuptaJonathan Berant
2020
Findings of EMNLP

Generalization of models to out-of-distribution (OOD) data has captured tremendous attention recently. Specifically, compositional generalization, i.e., whether a model generalizes to new structures… 

Learning from Task Descriptions

Orion WellerNick LourieMatt GardnerMatthew Peters
2020
EMNLP

Typically, machine learning systems solve new tasks by training on thousands of examples. In contrast, humans can solve new tasks by reading some instructions, with perhaps an example or two. To… 

MedICaT: A Dataset of Medical Images, Captions, and Textual References

Sanjay SubramanianLucy Lu WangSachin MehtaHannaneh Hajishirzi
2020
Findings of EMNLP

Understanding the relationship between figures and text is key to scientific document understanding. Medical figures in particular are quite complex, often consisting of several subfigures (75% of… 

MOCHA: A Dataset for Training and Evaluating Generative Reading Comprehension Metrics

Anthony ChenGabriel StanovskyS. SinghMatt Gardner
2020
EMNLP

Posing reading comprehension as a generation problem provides a great deal of flexibility, allowing for open-ended questions with few restrictions on possible answers. However, progress is impeded… 

Multilevel Text Alignment with Cross-Document Attention

Xuhui ZhouNikolaos PappasNoah A. Smith
2020
EMNLP

Text alignment finds application in tasks such as citation recommendation and plagiarism detection. Existing alignment methods operate at a single, predefined level and cannot learn to align texts… 

Multi-Step Inference for Reasoning over Paragraphs

Jiangming LiuMatt GardnerShay B. CohenMirella Lapata
2020
EMNLP

Complex reasoning over text requires understanding and chaining together free-form predicates and logical connectives. Prior work has largely tried to do this either symbolically or with black-box… 

Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs

Ana MarasovićChandra BhagavatulaJ. ParkYejin Choi
2020
Findings of EMNLP

Natural language rationales could provide intuitive, higher-level explanations that are easily understandable by humans, complementing the more broadly studied lower-level explanations based on… 

Parsing with Multilingual BERT, a Small Treebank, and a Small Corpus

Ethan C. ChauLucy H. LinNoah A. Smith
2020
Findings of EMNLP

Pretrained multilingual contextual representations have shown great success, but due to the limits of their pretraining data, their benefits do not apply equally to all language varieties. This… 

Plug and Play Autoencoders for Conditional Text Generation

Florian MaiNikolaos PappasI. MonteroNoah A. Smith
2020
EMNLP

Text autoencoders are commonly used for conditional generation tasks such as style transfer. We propose methods which are plug and play, where any pretrained autoencoder can be used, and only…