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

Commonly Uncommon: Semantic Sparsity in Situation Recognition

Mark YatskarVicente OrdonezLuke Zettlemoyerand Ali Farhadi
2017
CVPR

Semantic sparsity is a common challenge in structured visual classification problems; when the output space is complex, the vast majority of the possible predictions are rarely, if ever, seen in the… 

Crowdsourcing Multiple Choice Science Questions

Johannes WelblNelson F. Liuand Matt Gardner
2017
EMNLP • Workshop on Noisy User-generated Text

We present a novel method for obtaining high-quality, domain-targeted multiple choice questions from crowd workers. Generating these questions can be difficult without trading away originality,… 

Deep Semantic Role Labeling: What Works and What's Next

Luheng HeKenton LeeMike LewisLuke S. Zettlemoyer
2017
ACL

We introduce a new deep learning model for semantic role labeling (SRL) that significantly improves the state of the art, along with detailed analyses to reveal its strengths and limitations. We use… 

Distilling Task Knowledge from How-To Communities

Cuong Xuan ChuNiket Tandonand Gerhard Weikum
2017
WWW

Knowledge graphs have become a fundamental asset for search engines. A fair amount of user queries seek information on problem-solving tasks such as building a fence or repairing a bicycle. However,… 

Domain-Targeted, High Precision Knowledge Extraction

Bhavana DalviNiket Tandonand Peter Clark
2017
TACL

Our goal is to construct a domain-targeted, high precision knowledge base (KB), containing general (subject,predicate,object) statements about the world, in support of a downstream… 

End-to-End Neural Ad-hoc Ranking with Kernel Pooling

Chenyan XiongZhuyun DaiJamie Callanand Russell Power
2017
SIGIR

This paper proposes K-NRM, a kernel based neural model for document ranking. Given a query and a set of documents, K-NRM uses a translation matrix that models word-level similarities via word… 

End-to-end Neural Coreference Resolution

Kenton LeeLuheng HeMike Lewisand Luke Zettlemoyer
2017
EMNLP

We introduce the first end-to-end coreference resolution model and show that it significantly outperforms all previous work without using a syntactic parser or handengineered mention detector. The… 

Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding

Chenyan XiongRussell Power and Jamie Callan
2017
WWW

This paper introduces Explicit Semantic Ranking (ESR), a new ranking technique that leverages knowledge graph embedding. Analysis of the query log from our academic search engine,… 

How Good Are My Predictions? Efficiently Approximating Precision-Recall Curves for Massive Datasets

Ashish Sabharwal and Hanie Sedghi
2017
UAI

Large scale machine learning produces massive datasets whose items are often associated with a confidence level and can thus be ranked. However, computing the precision of these resources requires… 

Incorporating Ethics into Artificial Intelligence

Amitai Etzioni and Oren Etzioni
2017
Journal of Ethics

This article reviews the reasons scholars hold that driverless cars and many other AI equipped machines must be able to make ethical decisions, and the difficulties this approach faces. It then…