Addressing a question answering challenge by combining statistical methods with inductive rule learning and reasoning

Arindam Mitra, Chitta Baral

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

Abstract

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.

Original languageEnglish (US)
Title of host publication30th AAAI Conference on Artificial Intelligence, AAAI 2016
PublisherAAAI press
Pages2779-2785
Number of pages7
ISBN (Electronic)9781577357605
StatePublished - 2016
Event30th AAAI Conference on Artificial Intelligence, AAAI 2016 - Phoenix, United States
Duration: Feb 12 2016Feb 17 2016

Other

Other30th AAAI Conference on Artificial Intelligence, AAAI 2016
CountryUnited States
CityPhoenix
Period2/12/162/17/16

Fingerprint

Intelligent agents
Statistical methods
Inductive logic programming (ILP)
Knowledge representation
Processing
Computer programming languages

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Mitra, A., & Baral, C. (2016). Addressing a question answering challenge by combining statistical methods with inductive rule learning and reasoning. In 30th AAAI Conference on Artificial Intelligence, AAAI 2016 (pp. 2779-2785). AAAI press.

Addressing a question answering challenge by combining statistical methods with inductive rule learning and reasoning. / Mitra, Arindam; Baral, Chitta.

30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press, 2016. p. 2779-2785.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mitra, A & Baral, C 2016, Addressing a question answering challenge by combining statistical methods with inductive rule learning and reasoning. in 30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press, pp. 2779-2785, 30th AAAI Conference on Artificial Intelligence, AAAI 2016, Phoenix, United States, 2/12/16.
Mitra A, Baral C. Addressing a question answering challenge by combining statistical methods with inductive rule learning and reasoning. In 30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press. 2016. p. 2779-2785
Mitra, Arindam ; Baral, Chitta. / Addressing a question answering challenge by combining statistical methods with inductive rule learning and reasoning. 30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press, 2016. pp. 2779-2785
@inproceedings{56194a23e566434d9b3cd9735880be15,
title = "Addressing a question answering challenge by combining statistical methods with inductive rule learning and reasoning",
abstract = "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.",
author = "Arindam Mitra and Chitta Baral",
year = "2016",
language = "English (US)",
pages = "2779--2785",
booktitle = "30th AAAI Conference on Artificial Intelligence, AAAI 2016",
publisher = "AAAI press",

}

TY - GEN

T1 - Addressing a question answering challenge by combining statistical methods with inductive rule learning and reasoning

AU - Mitra, Arindam

AU - Baral, Chitta

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

SP - 2779

EP - 2785

BT - 30th AAAI Conference on Artificial Intelligence, AAAI 2016

PB - AAAI press

ER -