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.
How Shall a Machine Call a Thing?
Torrielli F.
First
;Rapp A.;Di Caro L.
2023-01-01
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.File | Dimensione | Formato | |
---|---|---|---|
How_shall_a_machine_call_a_thing___Camera_Ready_.pdf
Open Access dal 14/06/2024
Tipo di file:
POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione
379.48 kB
Formato
Adobe PDF
|
379.48 kB | Adobe PDF | Visualizza/Apri |
2023-NLDB.pdf
Accesso riservato
Tipo di file:
PDF EDITORIALE
Dimensione
366.68 kB
Formato
Adobe PDF
|
366.68 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.