The structure and performance of an open-domain question answering system

Authors

Dan Moldovan, Bobby B. Lyle School of Engineering
Sanda Harabagiu, Bobby B. Lyle School of Engineering
Marius Pasca, Bobby B. Lyle School of Engineering
Rada Mihalcea, Bobby B. Lyle School of Engineering
Roxana Girju, Bobby B. Lyle School of Engineering
Richard Goodrum, Bobby B. Lyle School of Engineering
Vasile Rus, Bobby B. Lyle School of Engineering

Abstract

This paper presents the architecture, operation and results obtained with the LASSO Question Answering system developed in the Natural Language Processing Laboratory at SMU. To find answers, the system relies on a combination of syntactic and semantic techniques. The search for the answer is based on a novel form of indexing called paragraph indexing. A score of 55.5% for short answers and 64.5% for long answers was achieved at the TREC-8 competition.

Publication Title

Proceedings of the Annual Meeting of the Association for Computational Linguistics

Recommended Citation

Moldovan, D., Harabagiu, S., Pasca, M., Mihalcea, R., Girju, R., Goodrum, R., & Rus, V. (2000). The structure and performance of an open-domain question answering system. Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2000-October Retrieved from https://digitalcommons.memphis.edu/facpubs/20045