This paper introduces the Unified Interactive Natural Understanding of the Italian Language (UINAUIL), a benchmark of six tasks for Italian Natural Language Understanding. We present a description of the tasks and software library that collects the data from the European Language Grid, harmonizes the data format, and exposes functionalities to facilitates data manipulation and the evaluation of custom models. We also present the results of tests conducted with available Italian and multilingual language models on UINAUIL, providing an updated picture of the current state of the art in Italian NLU.

UINAUIL: A Unified Benchmark for Italian Natural Language Understanding

Valerio Basile
;
Livio Bioglio;Cristina Bosco;Viviana Patti
2023-01-01

Abstract

This paper introduces the Unified Interactive Natural Understanding of the Italian Language (UINAUIL), a benchmark of six tasks for Italian Natural Language Understanding. We present a description of the tasks and software library that collects the data from the European Language Grid, harmonizes the data format, and exposes functionalities to facilitates data manipulation and the evaluation of custom models. We also present the results of tests conducted with available Italian and multilingual language models on UINAUIL, providing an updated picture of the current state of the art in Italian NLU.
2023
The 61st Annual Meeting of the Association for Computational Linguistics (ACL)
Toronto, Canada
9 - 14 Luglio 2023
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL)
Association for Computational Linguistics
3
348
356
9781959429708
https://aclanthology.org/2023.acl-demo.33/
Valerio Basile , Livio Bioglio , Alessio Bosca , Cristina Bosco, Viviana Patti
File in questo prodotto:
File Dimensione Formato  
90_Paper.pdf

Accesso aperto

Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 160.93 kB
Formato Adobe PDF
160.93 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/1963493
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact