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

Automatic Construction of Inference-Supporting Knowledge Bases

Peter ClarkNiranjan BalasubramanianSumithra Bhakthavatsalamand Oyvind Tafjord
2014
AKBC

While there has been tremendous progress in automatic database population in recent years, most of human knowledge does not naturally fit into a database form. For example, knowledge that "metal… 

Chinese Open Relation Extraction for Knowledge Acquisition

Yuen-Hsien TsengLung-Hao LeeShu-Yen Linand Anthony Fader
2014
EACL

This study presents the Chinese Open Relation Extraction (CORE) system that is able to extract entity-relation triples from Chinese free texts based on a series of NLP techniques, i.e., word… 

Freebase QA: Information Extraction or Semantic Parsing?

Xuchen YaoJonathan Berantand Benjamin Van Durme
2014
ACL • Workshop on Semantic Parsing

We contrast two seemingly distinct approaches to the task of question answering (QA) using Freebase: one based on information extraction techniques, the other on semantic parsing. Results over the… 

Insights Into Parallelism with Intensive Knowledge Sharing

Ashish Sabharwal and Horst Samulowitz
2014
International Conference on Principles and Practice of Constraint Programming

Novel search space splitting techniques have recently been successfully exploited to paralleliz Constraint Programming and Mixed Integer Programming solvers. We first show how universal hashing can… 

Modeling Biological Processes for Reading Comprehension

Jonathan BerantVivek SrikumarPei-Chun Chenand Peter Clark
2014
EMNLP

Machine reading calls for programs that read and understand text, but most current work only attempts to extract facts from redundant web-scale corpora. In this paper, we focus on a new reading… 

Open Question Answering Over Curated and Extracted Knowledge Bases

Anthony FaderLuke Zettlemoyerand Oren Etzioni
2014
KDD

We consider the problem of open-domain question answering (Open QA) over massive knowledge bases (KBs). Existing approaches use either manually curated KBs like Freebase or KBs automatically… 

Discourse Complements Lexical Semantics for Non-factoid Answer Reranking

Peter JansenMihai Surdeanuand Peter Clark
2014
ACL

We propose a robust answer reranking model for non-factoid questions that integrates lexical semantics with discourse information, driven by two representations of discourse: a shallow… 

A Lightweight and High Performance Monolingual Word Aligner

Xuchen YaoBenjamin Van DurmeChris Callision-Burchand Peter Clark
2013
ACL

Fast alignment is essential for many natural language tasks. But in the setting of monolingual alignment, previous work has not been able to align more than one sentence pair per second. We describe… 

Automatic Coupling of Answer Extraction and Information Retrieval

Xuchen YaoBenjamin Van Durmeand Peter Clark
2013
ACL

Information Retrieval (IR) and Answer Extraction are often designed as isolated or loosely connected components in Question Answering (QA), with repeated overengineering on IR, and not necessarily… 

Answer Extraction as Sequence Tagging with Tree Edit Distance

Xuchen YaoBenjamin Van DurmeChris Callision-Burchand Peter Clark
2013
NAACL

Our goal is to extract answers from preretrieved sentences for Question Answering (QA). We construct a linear-chain Conditional Random Field based on pairs of questions and their possible answer…