Abstract

This paper aims to investigate the feasibility of utilising Large Language Models (LLMs) and Latent Diffusion Models (LDMs) for automatically categorising word basicness and concreteness, i.e. two well-known aspects of language having significant relevance on tasks such as text simplification. To achieve this, we propose two distinct approaches: i) a generative Transformer-based LLM, and ii) a image+text multi-modal pipeline, referred to as stableKnowledge, which utilises a LDM to map terms to the image level. The evaluation results indicate that while the LLM approach is particularly well-suited for recognising word basicness, stableKnowledge outperforms the former when the task shifts to measuring concreteness.

Note: This work is based on the author’s Master’s thesis, which received a Special Mention at the AIxIA “Leonardo Lesmo” Award for best AI Master Thesis in 2023.

Citation

Federico Torrielli, Amon Rapp, and Luigi Di Caro, “How Shall a Machine Call a Thing?” in Natural Language Processing and Information Systems - 28th International Conference on Applications of Natural Language to Information Systems, NLDB 2023, Derby, UK, June 21-23, 2023, Proceedings, Elisabeth Métais, Farid Meziane, Vijayan Sugumaran, Warren Manning, and Stephan Reiff-Marganiec, Eds., ser. Lecture Notes in Computer Science, vol. 13913, Springer, 2023, pp. 546–557. DOI: 10.1007/978-3-031-35320-8_41

@inproceedings{DBLP:conf/nldb/TorrielliRC23,
	title        = {How Shall a Machine Call a Thing?},
	author       = {Federico Torrielli and Amon Rapp and Luigi Di Caro},
	year         = 2023,
	booktitle    = {Natural Language Processing and Information Systems - 28th International Conference on Applications of Natural Language to Information Systems, {NLDB} 2023, Derby, UK, June 21-23, 2023, Proceedings},
	publisher    = {Springer},
	series       = {Lecture Notes in Computer Science},
	volume       = 13913,
	pages        = {546--557},
	doi          = {10.1007/978-3-031-35320-8_41},
	url          = {https://doi.org/10.1007/978-3-031-35320-8_41},
	editor       = {Elisabeth M{\'{e}}tais and Farid Meziane and Vijayan Sugumaran and Warren Manning and Stephan Reiff{-}Marganiec},
	timestamp    = {Fri, 07 Jul 2023 23:30:36 +0200},
	biburl       = {https://dblp.org/rec/conf/nldb/TorrielliRC23.bib},
	bibsource    = {dblp computer science bibliography, https://dblp.org}
}

Awards

Special Mention - AIxIA “Leonardo Lesmo” Award for best AI Master Thesis (2023)

Master’s Thesis

This paper is based on the Master’s thesis:
“How shall a machine call a thing?” Exploring Basicness in Language through Attention-based Neural Networks and Human-in-the-Loop Methodology
Final Vote: 110L/110 with dignity of printing
University of Torino, 2023