Learning to Understand Web Site Update Requests
Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 1028-1032.
Abstract
Although Natural Language Processing (NLP) for requests for information has been well-studied, there has been little prior work on understanding requests to update information. In this paper, we propose an intelligent system that can process natural language website update requests semi-automatically. In particular, this system can analyze requests, posted via email, to update the factual content of individual tuples in a databasebacked website. Users’ messages are processed using a scheme decomposing their requests into a sequence of entity recognition and text classification tasks. Using a corpus generated by human-subject experiments, we experimentally evaluate the performance of this system, as well as its robustness in handling request types not seen in training, or user-specific language styles not seen in training.
@inproceedings{ijcai2005p164,
title = {Learning to Understand Web Site Update Requests},
author = {Cohen, William W. and Minkov, Einat and Tomasic, Anthony},
booktitle = {Proceedings of the Nineteenth International Joint Conference on
Artificial Intelligence, {IJCAI-05}},
publisher = {International Joint Conferences on Artificial Intelligence},
pages = {1028--1032},
year = {2005},
url = {https://ijcai.org/proceedings/2005/164},
}
TY - CPAPER TI - Learning to Understand Web Site Update Requests AU - Cohen, William W. AU - Minkov, Einat AU - Tomasic, Anthony T2 - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05 PB - International Joint Conferences on Artificial Intelligence PY - 2005 SP - 1028 EP - 1032 UR - https://ijcai.org/proceedings/2005/164 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
