Naturalness of an Utterance Based on the Automatically Retrieved Commonsense
Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 1696-1696.
Abstract
In this research we investigated user’s behavior while facing a system coping with common knowledge about keywords and compared it with not only classic word-spotting method but also with random text-mining. We show how even a simple implementation of our idea can enrich the conversation and increase the naturalness of computer’s utterances. Our results show that even very commonsensical utterances are more natural than classic approaches and also methods we developed to make a conversation more interesting. For arousing opinion exchange during the session, we will also briefly introduce our idea of combining latest NLP achievements into one holistic system where the main engine we want to base on commonsense processing and affective computing.
@inproceedings{ijcai2005p340,
title = {Naturalness of an Utterance Based on the Automatically Retrieved Commonsense},
author = {Rzepka, Rafal and Ge, Yali and Araki, Kenji},
booktitle = {Proceedings of the Nineteenth International Joint Conference on
Artificial Intelligence, {IJCAI-05}},
publisher = {International Joint Conferences on Artificial Intelligence},
pages = {1696--1696},
year = {2005},
url = {https://ijcai.org/proceedings/2005/340},
}
TY - CPAPER TI - Naturalness of an Utterance Based on the Automatically Retrieved Commonsense AU - Rzepka, Rafal AU - Ge, Yali AU - Araki, Kenji T2 - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05 PB - International Joint Conferences on Artificial Intelligence PY - 2005 SP - 1696 EP - 1696 UR - https://ijcai.org/proceedings/2005/340 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
