SAILabSiena Artificial Intelligence Lab

Elections go bananas: A First Large-scale Multilingual Study of Pluralia Tantum using LLMs

, Publications

Published in the Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), EACL 2026, Rabat, Morocco.

The paper studies pluralia tantum, nouns that lack a singular form such as "scissors", in Italian, Russian and English, using LLMs as annotators. OpenAI and DeepSeek models reached 51% to 89% accuracy on a hand-annotated test set, and large-scale automatic annotation of corpus sentences revealed patterns of morpho-semantic change.

Authors: Elena Spaziani, Kamyar Zeinalipour, Pierluigi Cassotti, Nina Tahmasebi.

Read the paper

All news