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

Learning Continuous-Time Bayesian Networks in Relational Domains: A Non-Parametric Approach

Shuo YangTushar KhotKristian Kerstingand Sriraam Natarajan
2016
AAAI

Many real world applications in medicine, biology, communication networks, web mining, and economics, among others, involve modeling and learning structured stochastic processes that evolve over… 

Selecting Near-Optimal Learners via Incremental Data Allocation

Ashish SabharwalHorst Samulowitzand Gerald Tesauro
2016
AAAI

We study a novel machine learning (ML) problem setting of sequentially allocating small subsets of training data amongst a large set of classifiers. The goal is to select a classifier that will give… 

Answering Elementary Science Questions by Constructing Coherent Scenes using Background Knowledge

Yang Li and Peter Clark
2015
EMNLP

Much of what we understand from text is not explicitly stated. Rather, the reader uses his/her knowledge to fill in gaps and create a coherent, mental picture or “scene” depicting what text appears… 

BDD-Guided Clause Generation

Brian KellAshish Sabharwaland Willem-Jan van Hoeve
2015
CPAIOR

Nogood learning is a critical component of Boolean satisfiability (SAT) solvers, and increasingly popular in the context of integer programming and constraint programming. We present a generic… 

Elementary School Science and Math Tests as a Driver for AI: Take the Aristo Challenge!

Peter Clark
2015
Proceedings of IAAI

While there has been an explosion of impressive, datadriven AI applications in recent years, machines still largely lack a deeper understanding of the world to answer questions that go beyond… 

Exploring Markov Logic Networks for Question Answering

Tushar KhotNiranjan BalasubramanianEric Gribkoffand Oren Etzioni
2015
EMNLP

Elementary-level science exams pose significant knowledge acquisition and reasoning challenges for automatic question answering. We develop a system that reasons with knowledge derived from… 

Higher-order Lexical Semantic Models for Non-factoid Answer Reranking

Daniel FriedPeter JansenGustave Hahn-Powelland Peter Clark
2015
TACL

Lexical semantic models provide robust performance for question answering, but, in general, can only capitalize on direct evidence seen during training. For example, monolingual alignment models… 

Learning Knowledge Graphs for Question Answering through Conversational Dialog

Ben HixonPeter Clarkand Hannaneh Hajishirzi
2015
NAACL

We describe how a question-answering system can learn about its domain from conversational dialogs. Our system learns to relate concepts in science questions to propositions in a fact corpus, stores… 

Semantic Role Labeling for Process Recognition Questions

Samuel LouvanChetan NaikVeronica Lynnand Peter Clark
2015
K-CAP • First International Workshop on Capturing Scientific Knowledge (SciKnow)

We consider a 4th grade level question answering task. We focus on a subset involving recognizing instances of physical, biological, and other natural processes. Many processes involve similar… 

Spinning Straw into Gold: Using Free Text to Train Monolingual Alignment Models for Non-factoid Question Answering

Rebecca SharpPeter JansenMihai Surdeanuand Peter Clark
2015
NAACL

Monolingual alignment models have been shown to boost the performance of question answering systems by "bridging the lexical chasm" between questions and answers. The main limitation of these…