Learning Strategies for Open-Domain Natural Language Question Answering
Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 1054-1059.
Abstract
We present an approach to automatically learning strategies for natural language question answering from examples composed of textual sources, questions, and answers. Our approach formulates QA as a problem of first order inference over a suitably expressive, learned representation. This framework draws on prior work in learning action and problem-solving strategies, as well as relational learning methods. We describe the design of a system implementing this model in the framework of natural language question answering for story comprehension. Finally, we compare our approach to three prior systems, and present experimental results demonstrating the efficacy of our model.
@inproceedings{ijcai2005p230,
title = {Learning Strategies for Open-Domain Natural Language Question Answering},
author = {Grois, Eugene and Wilkins, David C.},
booktitle = {Proceedings of the Nineteenth International Joint Conference on
Artificial Intelligence, {IJCAI-05}},
publisher = {International Joint Conferences on Artificial Intelligence},
pages = {1054--1059},
year = {2005},
url = {https://ijcai.org/proceedings/2005/230},
}
TY - CPAPER TI - Learning Strategies for Open-Domain Natural Language Question Answering AU - Grois, Eugene AU - Wilkins, David C. T2 - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05 PB - International Joint Conferences on Artificial Intelligence PY - 2005 SP - 1054 EP - 1059 UR - https://ijcai.org/proceedings/2005/230 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
