Towards a reliable annotation framework for crisis MT evaluation: Addressing error taxonomies and annotator agreement
Abstract
Publication Date:
2025
abstract:
This paper presents a detailed analysis of the annotation process used in the ITALERT (Italian
Emergency Response Text) corpus, specifically designed to evaluate the performance of neural
machine translation (NMT) systems and large language models (LLMs) in translating high-stakes
messages from Italian to English.
Emergency Response Text) corpus, specifically designed to evaluate the performance of neural
machine translation (NMT) systems and large language models (LLMs) in translating high-stakes
messages from Italian to English.
Iris type:
4.2 Abstract in Atti di convegno
Keywords:
ITALERT corpis, neural machine translation
List of contributors:
Staiano, Maria Carmen; Han, Lifeng; Monti, Johanna; Chiusaroli, Francesca
Full Text:
Book title:
Corpus Linguistics 2025