We present UniOR-MT, an agentic terminology-aware machine translation pipeline developed for the WMT 2026 Terminology Translation Shared Task. We compare five progressively enriched translation paths, each adding one component to isolate its individual contribution. We additionally submit a mixed system that selects, among the five candidate paths, the best candidate using a combined measure of terminology accuracy and document-level quality estimation. Evaluation results show that incorporating a bilingual glossary provides the most consistent benefit, while additional post-editing steps yield limited improvements, and can even degrade translation quality for Spanish–Basque in the official evaluation. The final system, which includes iterative QA feedback and a stronger fallback model, achieves the highest docCOMET scores in our internal evaluation.

The purpose of this paper is to investigate the ability of Large Language Models (LLMs) to identify relations among terms, with the goal of facilitating and accelerating the construction of thesauri and terminological resources. We investigate whether the use of LLMs in this context can provide a valuable initial set of relations, serving as a basis upon which professional terminologists can build, validate, and enrich domain-specific knowledge representations.

Terminological resources have proven crucial in many applications ranging from Computer-Aided Translation tools to authoring softwares and multilingual and cross-lingual information retrieval systems. Nonetheless, with the exception of a few felicitous examples, such as the IATE (Interactive Terminology for Europe) Termbank, many terminological resources are not available in standard formats, such as Term Base eXchange (TBX), thus preventing their sharing and reuse. Yet, these terminologies could be improved associating the correspondent ontology-based information. The research described in the present contribution demonstrates the process and the methodologies adopted in the automatic conversion into TBX of such type of resources, together with their semantic enrichment based on the formalization of ontological information into terminologies. We present a proof-of-concept using the Italian Linguistic Resource for the Archaeological domain (developed according to Thesauri and Guidelines of the Italian Central Institute for the Catalogue and Documentation). Further, we introduce the conversion tool developed to support the process of creating ontology-aware terminologies for improving interoperability and sharing of existing language technologies and data sets.

In this paper we describe the system submitted to the ELEXIS Monolingual Word Sense Alignment Task. We test different systems,which are two types of LSTMs and a system based on a pretrained Bidirectional Encoder Representations from Transformers (BERT)model, to solve the task. LSTM models use fastText pre-trained word vectors features with different settings. For training the models,we did not combine external data with the dataset provided for the task. We select a sub-set of languages among the proposed ones,namely a set of Romance languages, i.e., Italian, Spanish, Portuguese, together with English and Dutch. The Siamese LSTM withattention and PoS tagging (LSTM-A) performed better than the other two systems, achieving a 5-Class Accuracy score of 0.844 in theOverall Results, ranking the first position among five teams.