TY - GEN
T1 - Addressing a question answering challenge by combining statistical methods with inductive rule learning and reasoning
AU - Mitra, Arindam
AU - Baral, Chitta
N1 - Funding Information:
We thank NSF for the DataNet Federation Consortium grant OCI-0940841 and ONR for their grant N00014-13-1-0334 for partially supporting this research.
Publisher Copyright:
© Copyright 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2016
Y1 - 2016
N2 - A group of researchers from Facebook has recently proposed a set of 20 question-answering tasks (Facebook's bAbl dataset) as a challenge for the natural language understanding ability of an intelligent agent. These tasks are designed to measure various skills of an agent, such as: fact based question-answering, simple induction, the ability to find paths, co-reference resolution and many more. Their goal is to aid in the development of systems that can learn to solve such tasks and to allow a proper evaluation of such systems. They show existing systems cannot fully solve many of those toy tasks. In this work, we present a system that excels at all the tasks except one. The proposed model of the agent uses the Answer Set Programming (ASP) language as the primary knowledge representation and reasoning language along with the standard statistical Natural Language Processing (NLP) models. Given a training dataset containing a set of narrations, questions and their answers, the agent jointly uses a translation system, an Inductive Logic Programming algorithm and Statistical NLP methods to learn the knowledge needed to answer similar questions. Our results demonstrate that the introduction of a reasoning module significantly improves the performance of an intelligent agent.
AB - A group of researchers from Facebook has recently proposed a set of 20 question-answering tasks (Facebook's bAbl dataset) as a challenge for the natural language understanding ability of an intelligent agent. These tasks are designed to measure various skills of an agent, such as: fact based question-answering, simple induction, the ability to find paths, co-reference resolution and many more. Their goal is to aid in the development of systems that can learn to solve such tasks and to allow a proper evaluation of such systems. They show existing systems cannot fully solve many of those toy tasks. In this work, we present a system that excels at all the tasks except one. The proposed model of the agent uses the Answer Set Programming (ASP) language as the primary knowledge representation and reasoning language along with the standard statistical Natural Language Processing (NLP) models. Given a training dataset containing a set of narrations, questions and their answers, the agent jointly uses a translation system, an Inductive Logic Programming algorithm and Statistical NLP methods to learn the knowledge needed to answer similar questions. Our results demonstrate that the introduction of a reasoning module significantly improves the performance of an intelligent agent.
UR - http://www.scopus.com/inward/record.url?scp=85007201276&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85007201276&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85007201276
T3 - 30th AAAI Conference on Artificial Intelligence, AAAI 2016
SP - 2779
EP - 2785
BT - 30th AAAI Conference on Artificial Intelligence, AAAI 2016
PB - AAAI press
T2 - 30th AAAI Conference on Artificial Intelligence, AAAI 2016
Y2 - 12 February 2016 through 17 February 2016
ER -