The creation of a robust evaluation methodology is one of the pivotal issues for transfer learning between closely related lects. The current study proposes to resolve this issue by concisely implementing a group of evaluation methods that enable a more systematic qualitative analysis of errata (for instance, string similarity measures to assess lemmatisation more effectively). The paper introduces a robustness score, a metric that aims to assess the stabilityof model performance across different datasets. The case study is a morphosyntactic tagging of a small historical (beginning of the twentieth century) corpus of Lemko (Slavic clade, Transcarpathian area). It presents a diversity of cross-dependent tasks, made rather complex by the rich Lemko morphology, highly influenced by areal convergence processes. The tagger is a pre-trained Stanza. The study uses modern standard Ukrainian as the source language, as it is the closest to the Lemko high-resource lect. The analysis reveals that linguistically-aware metrics improve the speed and accuracy of analysis of the errata, especially those caused by the differences between source and target lects. The key data contribution is the open- source dataset of Lemko, obtained during the tagging tasks. Future research directions include a larger-scale test that applies more models to a more extensive material.

We explore the use of large language models (LLMs) for morphological disambiguation in Belarusian, a low-resource language. The pipeline has two stages: a rule-based analyzer generates candidate lemmas and grammatical tags, which an LLM then disambiguates in context. Initial evaluation of ChatGPT, Claude, and Gemini on a gold-standard sample shows high accuracy. We scale this approach to a 375K-word corpus using Gemini and compare the results against a neural baseline (Stanza). Manual review of discrepancies suggests that the LLM-based approach outperforms the baseline, offering a solution for corpus annotation in Belarusian.

While qualitative descriptions (in the form of reference grammars) and benchmarks for low-resource languages are becoming increasingly widespread, computational linguists do not often use quantitative methods to describe a new lect rather than a new model. This paper intends to close this lacuna. The case study is a Lemko text transcribed at the beginning of the twentieth century. Using morphosyntactic tagging and topic modelling, the study demonstrates areal influences and archaic features of the lect. Fine-grained evaluation significantly assists in identifying subtle patterns that are not readily apparent through traditional metrics such as accuracy score. The results highlight the necessity of a more detailed analysis of model performance, which may yield more linguistically significant results than a purely manual check. This information is present in the resulting dataset, which can be used for further investigation into the structural features of the Lemko lect.

The paper introduces TransVar – the corpus of the historical Transcarpathian lects (the first half of the XX century, the territories of modern Ukraine, Poland, Slovakia, and Romania). The corpus contains data from Lemko, Bojko and Hutsul small territorial lect groups. It is crucial for studies of the people of these territories, who witnessed forceful deportation from their homeland in the 1940s – 1950s, soon after the recordings were made (1920s – 1930s). The article also provides a brief overview of their linguistic properties, as evident in the material. The corpus is morphosyntactically tagged. It contains data on part-of-speech, morphological features, lemmata and syntactical dependencies. The study stresses the crux of manual analysis of the errata made in an automatic tagging phase for further improvement. The supplementary information includes named entities encountered in the text and the basic vocabulary. All the texts are accompanied by metalinguistic information, required for the sociolinguistic study. After the analysis of the current stage of the corpus creation, the article outlines further research prospects. Apart from more thorough manual annotation, one of the prospects is to add English translation with the purpose of making the material more accessible to scholars without a background in Slavic studies.

The paper presents a computer-assisted exploration of a set of texts, where qualitative analysis complements the linguistically-aware vector-based language distance measurements, interpreting them through close reading and thus proving or disproving their conclusions. It proposes using a method designed for small raw corpora to explore the individual, chronological, and gender-based differences within an extinct single territorial lect, known only by a scarce collection of documents. The material under consideration is the Novgorodian birchbark letters, a set of rather small manuscripts (not a single one is more than 1000 tokens) that are witnesses of the Old Novgorodian lect, spoken on the territories of modern Novgorod and Staraya Russa at the first half of the first millennium CE. The study shows the existence of chronological variation, a mild degree of individual variation, and almost absent gender-based differences. Possible prospects of the study include its application to the newly discovered birchbark letters and using an outgroup for more precise measurements.

Pre-trained language models have significantly advanced natural language processing (NLP), particularly in analyzing languages with complex morphological structures. This study addresses lemmatization for the Russian language, the errors in which can critically affect the performance of information retrieval, question answering, and other tasks. We present the results of experiments on generative lemmatization using pre-trained language models. Our findings demonstrate that combining generative models with the existing solutions allows achieving performance that surpasses current results for the lemmatization of Russian. This paper also introduces Rubic2, a new ensemble approach that combines the generative BART-base model, fine-tuned on a manually annotated data set of 2.1 million tokens, with the neural model called Rubic which is currently used for morphological annotation and lemmatization in the Russian National Corpus. Extensive experiments show that Rubic2 outperforms current solutions for the lemmatization of Russian, offering superior results across various text domains and contributing to advancements in NLP applications.

The study of low-resourced East Slavic lects is becoming increasingly relevant as they face the prospect of extinction under the pressure of standard Russian while being treated by academia as an inferior part of this lect. The Khislavichi lect, spoken in a settlement on the border of Russia and Belarus, is a perfect example of such an attitude. We take an alternative approach and study East Slavic lects (such as Khislavichi) as separate systems. The proposed method includes the development of a tagged corpus through morphological tagging with the models trained on the bigger lects. Morphological tagging results may be used to place these lects among the bigger ones, such as standard Belarusian or standard Russian. The implemented morphological taggers of standard Russian and standard Belarusian demonstrate an accuracy higher than the accuracy of multilingual models by 3 to 15%. The study suggests possible ways to adapt these taggers to the Khislavichi dataset, such as tagset unification and transcription closer to the actual sound rather than the standard lect pronunciation. Automatic classification supports the hypothesis that Khislavichi is a border East Slavic lect that historically was Belarusian but got russified: the algorithm places it either slightly closer to Russian or to Belarusian.

The article introduces a novel task of multi-lect automatic detection of Swadesh list items from raw corpora. The task aids the early stageof historical linguistics study by helping the researcher compile word lists for further analysis.In this paper, I test multi-lect automatic detection on the East Slavic lects’ data. The training data consists of Ukrainian, Belarusian, and Russian material. I introduce a new dataset for the Ukrainian language. I implement data augmentation techniques to give automatic tools a better understanding of the searched value. The test data consists of the Old East Slavic texts.I train HMM, CRF, and mBERT models, then test and evaluate them by harmonic F1 score. The baseline is a Random Forest classifier. I introduce two different subtasks: the search for new Swadesh list items, and the search for the known Swadesh list items in new lects of the well-established group. The first subtask, given the simultaneously diverse and vague nature of the Swadesh list, currently presents an almost unbeatable challenge for machine learning methods. The second subtask, on the other hand, is easier, and the mBERT model achieves a 0.57 F1 score. This is an impressive result, given how hard it is to formalise the token belonging to a very specific and thematically diverse set of concepts.

The growing need for using small data distinguished by a set of distributional properties becomes all the more apparent in the era of large language models (LLM). In this paper, we show that for the lemmatisation of the web as corpora texts, heterogeneous social media texts, and dialect texts, the morphological tagging by a model trained on a small dataset with specific properties generally works better than the morphological tagging by a model trained on a large dataset. The material we use is Russian non-standard texts and interviews with dialect speakers. The sequence-to-sequence lemmatisation with the help of taggers trained on smaller linguistically aware datasets achieves the average results of 85 to 90 per cent. These results are consistently (but not always), by 1-2 per cent. higher than the results of lemmatisation with the help of the large-dataset-trained taggers. We analyse these results and outline the possible further research directions.