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

Moving Beyond the Turing Test with the Allen AI Science Challenge

Carissa SchoenickPeter ClarkOyvind Tafjordand Oren Etzioni
2016
CACM

The field of Artificial Intelligence has made great strides forward recently, for example AlphaGo's recent victory against the world champion Lee Sedol in the game of Go, leading to great optimism… 

Probabilistic Models for Learning a Semantic Parser Lexicon

Jayant Krishnamurthy
2016
NAACL

We introduce several probabilistic models for learning the lexicon of a semantic parser. Lexicon learning is the first step of training a semantic parser for a new application domain and the quality… 

Question Answering via Integer Programming over Semi-Structured Knowledge

Daniel KhashabiTushar KhotAshish Sabharwaland Dan Roth
2016
IJCAI

Answering science questions posed in natural language is an important AI challenge. Answering such questions often requires non-trivial inference and knowledge that goes beyond factoid retrieval.… 

Semantic Parsing to Probabilistic Programs for Situated Question Answering

Jayant KrishnamurthyOyvind Tafjordand Aniruddha Kembhavi
2016
EMNLP

Situated question answering is the problem of answering questions about an environment such as an image or diagram. This problem requires jointly interpreting a question and an environment using… 

What's in an Explanation? Characterizing Knowledge and Inference Requirements for Elementary Science Exams

Peter JansenNiranjan BalasubramanianMihai Surdeanuand Peter Clark
2016
COLING

QA systems have been making steady advances in the challenging elementary science exam domain. In this work, we develop an explanation-based analysis of knowledge and inference requirements, which… 

My Computer is an Honor Student — but how Intelligent is it? Standardized Tests as a Measure of AI

Peter Clark and Oren Etzioni
2016
AI Magazine

Given the well-known limitations of the Turing Test, there is a need for objective tests to both focus attention on, and measure progress towards, the goals of AI. In this paper we argue that… 

Closing the Gap Between Short and Long XORs for Model Counting

Shengjia ZhaoSorathan ChaturapruekAshish Sabharwaland Stefano Ermon
2016
AAAI

Many recent algorithms for approximate model counting are based on a reduction to combinatorial searches over random subsets of the space defined by parity or XOR constraints. Long parity… 

Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions

Peter ClarkOren EtzioniDaniel Khashabiand Peter Turney
2016
AAAI

What capabilities are required for an AI system to pass standard 4th Grade Science Tests? Previous work has examined the use of Markov Logic Networks (MLNs) to represent the requisite background… 

Exact Sampling with Integer Linear Programs and Random Perturbations

Carolyn KimAshish Sabharwaland Stefano Ermon
2016
AAAI

We consider the problem of sampling from a discrete probability distribution specified by a graphical model. Exact samples can, in principle, be obtained by computing the mode of the original model… 

Hierarchical Semi-supervised Classification with Incomplete Class Hierarchies

Bhavana DalviAditya Mishraand William W. Cohen
2016
WSDM

In an entity classification task, topic or concept hierarchies are often incomplete. Previous work by Dalvi et al. has shown that in non-hierarchical semi-supervised classification tasks, the…