TY - GEN
T1 - Declarative question answering over knowledge bases containing natural language text with answer set programming
AU - Mitra, Arindam
AU - Clark, Peter
AU - Tafjord, Oyvind
AU - Baral, Chitta
N1 - Funding Information:
Acknowledgment The authors would like to thank Tushar Khot for his tremendous support during the experiments. The research is partially funded by NSF 1816039 and AI2 Key Scientific Challenges Program.
Publisher Copyright:
© 2019, Association for the Advancement of Artificial Intelligence (www.aaai.org).
PY - 2019
Y1 - 2019
N2 - While in recent years machine learning (ML) based approaches have been the popular approach in developing end-to-end question answering systems, such systems often struggle when additional knowledge is needed to correctly answer the questions. Proposed alternatives involve translating the question and the natural language text to a logical representation and then use logical reasoning. However, this alternative falters when the size of the text gets bigger. To address this we propose an approach that does logical reasoning over premises written in natural language text. The proposed method uses recent features of Answer Set Programming (ASP) to call external NLP modules (which may be based on ML) which perform simple textual entailment. To test our approach we develop a corpus based on the life cycle questions and showed that Our system achieves up to 18% performance gain when compared to standard MCQ solvers.
AB - While in recent years machine learning (ML) based approaches have been the popular approach in developing end-to-end question answering systems, such systems often struggle when additional knowledge is needed to correctly answer the questions. Proposed alternatives involve translating the question and the natural language text to a logical representation and then use logical reasoning. However, this alternative falters when the size of the text gets bigger. To address this we propose an approach that does logical reasoning over premises written in natural language text. The proposed method uses recent features of Answer Set Programming (ASP) to call external NLP modules (which may be based on ML) which perform simple textual entailment. To test our approach we develop a corpus based on the life cycle questions and showed that Our system achieves up to 18% performance gain when compared to standard MCQ solvers.
UR - http://www.scopus.com/inward/record.url?scp=85074784729&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85074784729&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85074784729
T3 - 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019
SP - 3003
EP - 3010
BT - 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019
PB - AAAI press
T2 - 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Annual Conference on Innovative Applications of Artificial Intelligence, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019
Y2 - 27 January 2019 through 1 February 2019
ER -