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

Iterative Search for Weakly Supervised Semantic Parsing

Pradeep DasigiMatt GardnerShikhar MurtyEd Hovy
2019
NAACL

Training semantic parsers from question-answer pairs typically involves searching over an exponentially large space of logical forms, and an unguided search can easily be misled by spurious logical… 

Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets

Nelson F. LiuRoy SchwartzNoah Smith
2019
NAACL

Several datasets have recently been constructed to expose brittleness in models trained on existing benchmarks. While model performance on these challenge datasets is significantly lower compared… 

A General Framework for Information Extraction Using Dynamic Span Graphs

Yi LuanDave WaddenLuheng HeHannaneh Hajishirzi
2019
NAACL

We introduce a general framework for several information extraction tasks that share span representations using dynamically constructed span graphs. The graphs are dynamically constructed by… 

Text Generation from Knowledge Graphs with Graph Transformers

Rik Koncel-KedziorskiDhanush BekalYi LuanHannaneh Hajishirzi
2019
NAACL

Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohibitively expensive… 

MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms

ida AminiSaadia GabrielPeter LinHannaneh Hajishirzi
2019
NAACL

We introduce a large-scale dataset of math word problems and an interpretable neural math problem solver by learning to map problems to their operation programs. Due to annotation challenges,… 

Benchmarking Hierarchical Script Knowledge

Yonatan BiskJan BuysKarl PichottaYejin Choi
2019
NAACL

Understanding procedural language requires reasoning about both hierarchical and temporal relations between events. For example, “boiling pasta” is a sub-event of “making a pasta dish”, typically… 

Neural network gradient-based learning of black-box function interfaces

Alon JacoviGuy HadashEinat KermanyJonathan Berant
2019
ICLR

Deep neural networks work well at approximating complicated functions when provided with data and trained by gradient descent methods. At the same time, there is a vast amount of existing functions… 

FlowQA: Grasping Flow in History for Conversational Machine Comprehension

Hsin-Yuan HuangEunsol ChoiWen-tau Yih
2019
ICLR

Conversational machine comprehension requires a deep understanding of the conversation history. To enable traditional, single-turn models to encode the history comprehensively, we introduce Flow, a… 

Visual Semantic Navigation using Scene Priors

Wei YangXiaolong WangAli FarhadiRoozbeh Mottaghi
2019
ICLR

How do humans navigate to target objects in novel scenes? Do we use the semantic/functional priors we have built over years to efficiently search and navigate? For example, to search for mugs, we… 

The Curious Case of Neural Text Degeneration

Ari HoltzmanJan BuysLi DuYejin Choi
2019
ICLR

Despite considerable advances in neural language modeling, it remains an open question what the best decoding strategy is for text generation from a language model (e.g. to generate a story). The…