Word Sense Disambiguation (WSD) has been widely evaluated using the semantic frameworks of WordNet, BabelNet, and the Oxford Dictionary of English. However, for the UCREL Semantic Analysis System (USAS) framework, no open extensive evaluation has been performed beyond lexical coverage or single language evaluation. In this work, we perform the largest semantic tagging evaluation of the rule based system that uses the lexical resources in the USAS framework covering five different languages using four existing datasets and one novel Chinese dataset. We create a new silver labelled English dataset, to overcome the lack of manually tagged training data, that we train and evaluate various mono and multilingual neural models in both mono and cross-lingual evaluation setups with comparisons to their rule based counterparts, and show how a rule based system can be enhanced with a neural network model. The resulting neural network models, including the data they were trained on, the Chinese evaluation dataset, and all of the code will be released as open resources.

Multilingual large language models (LLMs) often exhibit emergent ‘shadow’ capabilities in languages without official support, yet their performance on these languages remains uneven and under-measured. This is particularly acute for morphosyntactically rich minority languages such as Scottish Gaelic, where translation benchmarks fail to capture structural competence. We introduce GaelEval, the first multi-dimensional benchmark for Gaelic, comprising: (i) an expert-authored morphosyntactic MCQA task; (ii) a culturally-grounded translation benchmark and (iii) a large-scale cultural knowledge Q&A task. Evaluating 19 LLMs against a fluent-speaker human baseline (n = 30), we find that Gemini 3 Pro Preview achieves 83.3% accuracy on the linguistic task, surpassing the human baseline (78.1%). Proprietary models consistently outperform open-weight systems, and in-language (Gaelic) prompting yields a small but stable advantage (+2.4pp). On the cultural task, leading models exceed 90% accuracy, though most systems perform worse under Gaelic prompting and absolute scores are inflated relative to the manual benchmark. Overall, GaelEval reveals that frontier models achieve above-human performance on several dimensions of Gaelic grammar, demonstrates the effect of Gaelic prompting and shows a consistent performance gap favouring proprietary over open-weight models.

This paper reports the latest developments, planned works, and issues of the Corpas Náisiúnta na Gaeilge (henceforth: CNG, translation: the National Corpus of Irish) project, detailing the work that has been completed to date, current work, and planned future work. This report details the compilation of corpora, development of a project website and part-speech tagger, the challenges of expanding existing corpora, and the addition of historical and legal corpora. We also present the training and outreach activities of the project.

Large Language Models have been widely adopted in NLP tasks and applications, how- ever, their ability to accurately process Irish and other minority languages has not been fully explored. In this paper we describe prelim- inary experiments examining the capacity of publicly-available machine translation engines (Google Translate, Microsoft Bing, and eTrans- lation) and prompt-based AI systems systems (ChatGPT 3.5, Llama 2) for translating and handling challenging language features of Irish. A hand-crafted selection of challenging Irish language features were incorporated into trans- lation prompts, and the output from each model was examined by a human evaluator. The re- sults of these experiments indicate that these LLM-based models still struggle with translat- ing rare linguistic phenomena and ambiguous constructions. This preliminary analysis helps to inform further research in this field, pro- viding a simple ranking of publicly-available models, and indicating which language features require particular attention when evaluating model capacity.

The BERT family of neural language models have become highly popular due to their ability to provide sequences of text with rich context-sensitive token encodings which are able to generalise well to many NLP tasks. We introduce gaBERT, a monolingual BERT model for the Irish language. We compare our gaBERT model to multilingual BERT and the monolingual Irish WikiBERT, and we show that gaBERT provides better representations for a downstream parsing task. We also show how different filtering criteria, vocabulary size and the choice of subword tokenisation model affect downstream performance. We compare the results of fine-tuning a gaBERT model with an mBERT model for the task of identifying verbal multiword expressions, and show that the fine-tuned gaBERT model also performs better at this task. We release gaBERT and related code to the community.