Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
BDD-Guided Clause Generation
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!
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
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
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
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
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
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…
Automatic Construction of Inference-Supporting Knowledge Bases
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
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?
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…