Analogy Generation with HowNet
Abstract
Analogy is a powerful boundary-transcending process that exploits a conceptual system's ability to perform controlled generalization in one domain and re-specialization into another. The result of this semantic leap is the transference of meaning from one concept to another from which metaphor derives its name (literally: to carry over). Such generalization and respecialization can be achieved using a variety of representations and techniques, most notably abstraction via a taxonomic backbone, or selective projection via structure-mapping on propositional content. In this paper we explore the extent to which a bilingual lexical ontology for English and Chinese, called HowNet, can support both approaches to analogy.
Cite
Text
Veale. "Analogy Generation with HowNet." International Joint Conference on Artificial Intelligence, 2005.Markdown
[Veale. "Analogy Generation with HowNet." International Joint Conference on Artificial Intelligence, 2005.](https://mlanthology.org/ijcai/2005/veale2005ijcai-analogy/)BibTeX
@inproceedings{veale2005ijcai-analogy,
title = {{Analogy Generation with HowNet}},
author = {Veale, Tony},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2005},
pages = {1148-1153},
url = {https://mlanthology.org/ijcai/2005/veale2005ijcai-analogy/}
}