arXiv subjects

Dawn Knight

Publications and source records attributed to Dawn Knight.

7 recordsLinked to original sources

arXiv2026

ComplexityMT: Benchmarking the Interaction Between Text Complexity and Machine Translation

When a text is translated, does the translation retain the complexity of the original? We introduce ComplexityMT, a new challenge for assessing how text complexity and machine translation interact with and influence each other, using the Common European Framework of Reference for Languages (CEFR) levels as the measure of text complexity. Across six languages, including Arabic, Dutch, English, French, Hindi, and Russian, we evaluate three open-weight models, one closed model, and a commercial machine translation system on two tasks: i) correlation of CEFR with translation difficulty, and ii) shifts in CEFR levels of the source texts. Our experiments show that higher CEFR levels make texts more difficult to translate and that machine translation lowers the target text's CEFR level for most languages at the document level. These findings provide new insights for researchers and practitioners working on multilingual pedagogical content generation and MT difficulty estimation.

cs.CL↗

arXiv2026

GaelEval: Benchmarking LLM Performance for Scottish Gaelic

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 (+$2.4\%$). 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.

cs.CL↗

arXiv2026

FreeTxt-Vi: A Benchmarked Vietnamese-English Toolkit for Segmentation, Sentiment, and Summarisation

FreeTxt-Vi is a free and open source web based toolkit for creating and analysing bilingual Vietnamese English text collections. Positioned at the intersection of corpus linguistics and natural language processing NLP it enables users to build explore and interpret free text data without requiring programming expertise. The system combines corpus analysis features such as concordancing keyword analysis word relation exploration and interactive visualisation with transformer based NLP components for sentiment analysis and summarisation. A key contribution of this work is the design of a unified bilingual NLP pipeline that integrates a hybrid VnCoreNLP and Byte Pair Encoding BPE segmentation strategy a fine tuned TabularisAI sentiment classifier and a fine tuned Qwen2.5 model for abstractive summarisation. Unlike existing text analysis platforms FreeTxt Vi is evaluated as a set of language processing components. We conduct a three part evaluation covering segmentation sentiment analysis and summarisation and show that our approach achieves competitive or superior performance compared to widely used baselines in both Vietnamese and English. By reducing technical barriers to multilingual text analysis FreeTxt Vi supports reproducible research and promotes the development of language resources for Vietnamese a widely spoken but underrepresented language in NLP. The toolkit is applicable to domains including education digital humanities cultural heritage and the social sciences where qualitative text data are common but often difficult to process at scale.

cs.CL↗

arXiv2026

Creating a Hybrid Rule and Neural Network Based Semantic Tagger using Silver Standard Data: the PyMUSAS framework for Multilingual Semantic Annotation

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 have been released as open resources.

cs.CL↗

arXiv2025

UniversalCEFR: Enabling Open Multilingual Research on Language Proficiency Assessment

We introduce UniversalCEFR, a large-scale multilingual and multidimensional dataset of texts annotated with CEFR (Common European Framework of Reference) levels in 13 languages. To enable open research in automated readability and language proficiency assessment, UniversalCEFR comprises 505,807 CEFR-labeled texts curated from educational and learner-oriented resources, standardized into a unified data format to support consistent processing, analysis, and modelling across tasks and languages. To demonstrate its utility, we conduct benchmarking experiments using three modelling paradigms: a) linguistic feature-based classification, b) fine-tuning pre-trained LLMs, and c) descriptor-based prompting of instruction-tuned LLMs. Our results support using linguistic features and fine-tuning pretrained models in multilingual CEFR level assessment. Overall, UniversalCEFR aims to establish best practices in data distribution for language proficiency research by standardising dataset formats, and promoting their accessibility to the global research community.

cs.CL↗

arXiv2022

Introducing the Welsh Text Summarisation Dataset and Baseline Systems

Welsh is an official language in Wales and is spoken by an estimated 884,300 people (29.2% of the population of Wales). Despite this status and estimated increase in speaker numbers since the last (2011) census, Welsh remains a minority language undergoing revitalization and promotion by Welsh Government and relevant stakeholders. As part of the effort to increase the availability of Welsh digital technology, this paper introduces the first Welsh summarisation dataset, which we provide freely for research purposes to help advance the work on Welsh text summarization. The dataset was created by Welsh speakers by manually summarising Welsh Wikipedia articles. In addition, the paper discusses the implementation and evaluation of different summarisation systems for Welsh. The summarization systems and results will serve as benchmarks for the development of summarises in other minority language contexts.

cs.CL↗

arXiv2020

The National Corpus of Contemporary Welsh: Project Report | Y Corpws Cenedlaethol Cymraeg Cyfoes: Adroddiad y Prosiect

This report provides an overview of the CorCenCC project and the online corpus resource that was developed as a result of work on the project. The report lays out the theoretical underpinnings of the research, demonstrating how the project has built on and extended this theory. We also raise and discuss some of the key operational questions that arose during the course of the project, outlining the ways in which they were answered, the impact of these decisions on the resource that has been produced and the longer-term contribution they will make to practices in corpus-building. Finally, we discuss some of the applications and the utility of the work, outlining the impact that CorCenCC is set to have on a range of different individuals and user groups.

cs.CL↗