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

Probabilistic Neural Programs

Kenton W. Murray and Jayant Krishnamurthy
2016
NIPS • NAMPI Workshop

We present probabilistic neural programs, a framework for program induction that permits flexible specification of both a computational model and inference algorithm while simultaneously enabling… 

Tables as Semi-structured Knowledge for Question Answering

Sujay Kumar JauharPeter D. TurneyEduard Hovy
2016
ACL

Question answering requires access to a knowledge base to check facts and reason about information. Knowledge in the form of natural language text is easy to acquire, but difficult for automated… 

Adaptive Concentration Inequalities for Sequential Decision Problems

Shengjia ZhaoEnze ZhouAshish Sabharwaland Stefano Ermon
2016
NIPS

A key challenge in sequential decision problems is to determine how many samples are needed for an agent to make reliable decisions with good probabilistic guarantees. We introduce Hoeffding-like… 

Beyond Parity Constraints: Fourier Analysis of Hash Functions for Inference

Tudor AchimAshish Sabharwaland Stefano Ermon
2016
ICML

Random projections have played an important role in scaling up machine learning and data mining algorithms. Recently they have also been applied to probabilistic inference to estimate properties of… 

Creating Causal Embeddings for Question Answering with Minimal Supervision

Rebecca SharpMihai SurdeanuPeter Jansenand Peter Clark
2016
EMNLP

A common model for question answering (QA) is that a good answer is one that is closely related to the question, where relatedness is often determined using generalpurpose lexical models such as… 

Cross-Sentence Inference for Process Knowledge

Samuel LouvanChetan NaikSadhana Kumaraveland Peter Clark
2016
EMNLP

For AI systems to reason about real world situations, they need to recognize which processes are at play and which entities play key roles in them. Our goal is to extract this kind of rolebased… 

Examples are not enough. Learn to criticize! Criticism for Interpretability

Been KimSanmi Koyejo and Rajiv Khanna
2016
NIPS

Example-based explanations are widely used in the effort to improve the interpretability of highly complex distributions. However, prototypes alone are rarely sufficient to represent the gist of the… 

IKE - An Interactive Tool for Knowledge Extraction

Bhavana DalviSumithra BhakthavatsalamChris Clarkand Dirk Groeneveld
2016
AKBC

Recent work on information extraction has suggested that fast, interactive tools can be highly effective; however, creating a usable system is challenging, and few publicly available tools exist. In… 

Instructable Intelligent Personal Agent

Amos AzariaJayant Krishnamurthyand Tom M. Mitchell
2016
AAAI

Unlike traditional machine learning methods, humans often learn from natural language instruction. As users become increasingly accustomed to interacting with mobile devices using speech, their… 

Metaphor as a Medium for Emotion: An Empirical Study

Saif M. MohammadEkaterina Shutovaand Peter D. Turney
2016
SEM

It is generally believed that a metaphor tends to have a stronger emotional impact than a literal statement; however, there is no quantitative study establishing the extent to which this is true.…