Towards a Better Rational Speech Act Framework for Context-Aware Modeling of Metaphor Understanding
Abstract
Modeling language is a fundamental step for understanding human communication and improving human-computer interaction. The Rational Speech Act (RSA) model provides a flexible framework to pursue this objective by catching pragmatic reasoning. However, state-of-the-art models still have limitations in dealing with context. We present a new RSA framework for metaphor understanding that accounts explicitly for the role of context by emphasizing the mutual shared information between the speaker and the listener in the estimation of the communicative goal. The model is tested extensively against 24 metaphors (with either intrinsic or emergent properties) and its predictions are compared to human data.
Cite
Text
Carenini et al. "Towards a Better Rational Speech Act Framework for Context-Aware Modeling of Metaphor Understanding." ICML 2023 Workshops: ToM, 2023.Markdown
[Carenini et al. "Towards a Better Rational Speech Act Framework for Context-Aware Modeling of Metaphor Understanding." ICML 2023 Workshops: ToM, 2023.](https://mlanthology.org/icmlw/2023/carenini2023icmlw-better/)BibTeX
@inproceedings{carenini2023icmlw-better,
title = {{Towards a Better Rational Speech Act Framework for Context-Aware Modeling of Metaphor Understanding}},
author = {Carenini, Gaia and Bischetti, Luca and Schaeken, Walter and Bambini, Valentina},
booktitle = {ICML 2023 Workshops: ToM},
year = {2023},
url = {https://mlanthology.org/icmlw/2023/carenini2023icmlw-better/}
}