We study the problem of preserving offensive load in LLM-generated translations, focusing on how offensive words retain their load across languages. We draw on HurtNet, a novel language resource consisting of five multilingual (Arabic, French, Bulgarian, Greek, and Italian) dictionaries of hurtful terms, with multiple definitions and examples of usage. We draw on HurtNet to identify offensive senses shared by the 5 languages and the terms that denote them, and feed translations with this knowledge. We evaluate the approach through quantitative and qualitative analysis. A series of knowledge-injection zero-shot translation experiments were carried out with four different prompts that gradually increase injected linguistic knowledge, and three LLMs —an open use, a translation-dedicated, and a commercial one. Our results show that translations better preserving offensive load are produced when the prompt explicitly instructs the model about the translated offensive term and that the method is beneficial for those cases where the literal translation of the term does not preserve its offensive load.

This paper describes the LiITA Knowledge Base of interoperable linguistic resources for Italian.By adhering to the Linked Open Data principles, LiITA ensures and facilitates interoperability between distributed resources. The paper outlines the lemma-centered architecture of the Knowledge Base and details its core component: the Lemma Bank, a collection of Italian lemmas designed to interlink distributed lexical and textual resources.

The paper introduces the LiIta Knowledge Base of interoperable linguistic resources for Italian. After describing the principles of the Linked Data paradigm, on which LiIta is grounded, the paper presents the lemma-centred architecture of the Knowledge Base and details its core component, consisting of a large collection of Italian lemmas (called the Lemma Bank) used to interlink distributed lexical and textual resources.

We present VerbAtlas, a new, hand-crafted lexical-semantic resource whose goal is to bring together all verbal synsets from WordNet into semantically-coherent frames. The frames define a common, prototypical argument structure while at the same time providing new concept-specific information. In contrast to PropBank, which defines enumerative semantic roles, VerbAtlas comes with an explicit, cross-frame set of semantic roles linked to selectional preferences expressed in terms of WordNet synsets, and is the first resource enriched with semantic information about implicit, shadow, and default arguments. We demonstrate the effectiveness of VerbAtlas in the task of dependency-based Semantic Role Labeling and show how its integration into a high-performance system leads to improvements on both the in-domain and out-of-domain test sets of CoNLL-2009. VerbAtlas is available at http://verbatlas.org.