«Language: Codification, Competence, Communication»

USING LLMs FOR CROSS-LINGUAL STYLISTIC ADAPTATION OF CHILDREN’S FICTION

Yevheniia Dehtiarova — Wed, 31 Dec 2025 00:00:00 +0200

Background. In translating children’s literature, not only semantic accuracy but also stylistic fidelity to the original – intonational expressiveness, lexical accessibility, and age appropriateness – play a crucial role. Within cross-lingual adaptation, these factors require a delicate balance between cultural specificity and readability. Contemporary large language models (LLMs), such as GPT, offer new possibilities for automated and semi-automated translation, raising the question: how effective are they in preserving stylistic features when translating children’s fiction?

Purpose. This article explores the potential of large language models for cross-lingual stylistic adaptation of Ukrainian children’s literary texts into French, taking into account intonational, stylistic, and age-related specificities.

Methods. The study employs methods of contrastive analysis, stylistic examination of original texts and their translations, and experimental translation using an LLM (ChatGPT-4). The outcomes are evaluated in terms of register appropriateness, intonation transfer, narrative structure retention, and emotional tone.

Results. LLMs demonstrate a high level of grammatical and lexical precision, stylistic flexibility, and adaptability to child-oriented vocabulary. However, they tend to neutralize local cultural markers, may flatten the author’s unique style, and require well-designed prompts to preserve genre-specific features. At the same time, LLMs can generate multiple stylistically diverse translation options, enhancing the translator’s creative scope.

Discussion. LLMs can serve as effective tools for assisting in the translation of children’s literature, particularly in the initial stages of adaptation or in creating alternative versions. However, achieving stylistically precise and nuanced translation still requires the expertise of a professional human translator. Future research should focus on developing age- and culture-sensitive prompting strategies and improving evaluation frameworks for assessing stylistic adequacy in LLM-generated translations.

PILOT EXPERIMENT ON AUTOMATIC DETECTION OF VIETNAMESE MEDIA NARRATIVES ABOUT THE RUSSIA-UKRAINE WAR UNDER LIMITED RESOURCES

Viktoriia Musiichuk — Wed, 31 Dec 2025 00:00:00 +0200

Background. Narratives in media texts play a crucial role in shaping public opinion on international conflicts, including the Russia–Ukraine war. Systematic investigation of how Vietnamese media narratives are constructed is relevant both from a linguistic perspective and for developing effective strategies of international communication. Traditional narrative analysis is inefficient for large corpora due to its resource intensity, especially for low-resource languages such as Vietnamese (lack of annotated datasets, complex morpheme tokenization, limited access to multi-layered data). Existing studies are largely confined to qualitative discourse analysis of social media and do not employ scalable NLP-based automation.

Purpose. The aim of the article is to develop and test a hybrid methodology for the automated extraction of narratives from Vietnamese media texts under limited computational resources, combining classical narratology with digital humanities methods (NLP, clustering) in order to identify event-centric narrative axes (events, characters, frames) and provide their interpretation.

Methods. The study presents a pilot experiment on a corpus of 160 news items from Báo tin tức, collected via ParseHub and tokenized with Underthesea. An abductive approach (Burch, 2024) was implemented along two complementary strands: (1) an inductive strand using KeyBERT+PhoBERT/SimCSE-Vietnamese (text embeddings, keyphrase extraction) and GPT-4 (grouping into events/characters/themes); (2) a deductive strand using K-means/HDBSCAN+PhoBERT/SimCSE-Vietnamese (embeddings, clustering) and GPT-4 (cluster interpretation). All automatic outputs were subjected to manual verification.

Results. In the first strand, KeyBERT was used to extract keyphrases, which were subsequently mapped onto narrative labels (events, characters), aggregated into thematic groups and narrative frames with the assistance of GPT-4. In the second strand, parallel clustering was performed with K-means and HDBSCAN. The resulting clusters were interpreted and associated with narrative frames and core lexical items. Comparison of the two-vector approach revealed convergence in the extracted semantic axes and narrative frames. In both strands, Vietnamese news were found to prioritise coverage of the war’s impact on local and global economies, politics, and the humanitarian sphere over detailed analysis of military operations.

Discussion. The study demonstrates the effectiveness of the proposed methodology for automated detection of Vietnamese media narratives about the Russia–Ukraine war under limited resources. The abductive design proved methodologically valid, as both strands produced consistent and mutually reinforcing results. The workflow is robust in resource-limited environments such as Google Colab and is scalable to larger corpora. Future research may include systematic comparison of different corpora, integration of NER for character extraction, and dynamic narrative tracking using LSTM-based models, thereby contributing to the analysis of propagandistic and geopolitical discourses.

SELF-MENTIONS IN BRITISH PRIME MINISTER’S SPEECHES ON CLIMATE CHANGE

Oleksandr Kapranov — Wed, 31 Dec 2025 00:00:00 +0200

Background. In the United Kingdom (the UK), the issue of climate change has become a contentious problem that is regularly elucidated by the British media, the public at large, and by a number of climate change protest movements. Whilst there are competing discursive voices on climate change in the UK, it seems quite sensible to heed to the discourse on climate change by the current Labour government, which is led by Keir Starmer. Whereas his premiership is short, it seems, nevertheless, pertinent to look at Starmer’s discourse on climate change in more detail, given that Starmer determines the UK’s government policies associated with the issue of climate change. In this regard, it should be mentioned that there are several recent studies on the lexico-syntactic peculiarities of Starmer’s climate change discourse. At the same time, however, a score of other discursive and rhetorical aspects of Starmer’s discourse on climate change have not been analysed yet.

Purpose. The article involves a quantitative study that examines the frequency of self-mentions, which are manifested by the first person pronouns in Starmer’s speeches on climate change. It is argued in the study self-mentions may help to uncover the way Starmer frames the issue climate change, for instance, whether or not he presents himself as a team player, who looks at climate change as a challenge posed to the entire government and/or the entire British nation, or, alternatively, his use of self-mentions may reveal that he portrays himself as the sole fighter against the negative consequences of climate change. In this light, the study aims at answering the following research question: What is the frequency of self-mentions (i.e., “I”, “my”, “me”, “mine”, “myself”, “we”, “our”, “us”, “ours”, and “ourselves”) in Keir Starmer’s political speeches on climate change?

Methods. Methodologically, the study involves a quantitative procedure of computing the frequency of self-mentions in the corpus. To that end, the computer program AntConc is used in order to calculate the total number of occurrences of self-mentions in the corpus. To do so, Starmer’s speeches in corpus are processed separately in AntConc and, thereafter, the means and standard deviations of each type of self-mentions are computed.

Results. The results of the corpus analysis reveal that Starmer’s speeches on the issue of climate change involve the following types of self-mentions: “I”, “me”, “my”, “myself”, “we”, “us”, “our”, and “ourselves”. Judging from these findings, Starmer and/or his speechwriters do not employ the self-mentions “mine” and “ours”, respectively. Instead, they seem to capitalise on the frequent use of the self-mentions “we”, “our”, and “I”.

Discussion. The self-mention “we” both in absolute values and in normalised values per 1 000 words is the most frequently occurring self-mention in the corpus. This finding lends indirect support to the prior literature (Abdulla & Ahmed, 2024; Junianto, 2025; Liu, 2024; Phanthaphoommee & Munday, 2024; Romadlani, 2024; Williams & Wright, 2024), which posits that “we” seems to be a highly frequent self-mention in political discourses, especially in the Anglophone ones. “We” is employed by Starmer in its exclusive form rather often. In this regard, the literature (Hyland, 2001, 2002, 2004; Kapranov, 2024c) distinguishes between two forms of the self-mention “we”, the so-called inclusive “we” and exclusive “we”, respectively. The inclusive “we” presupposes such communicative situations, in which the speaker involves the addressee into the same domain, i.e. creates discursive togetherness with the audience, in which the speaker and the audience are treated as one collective body of people. In contrast to the inclusive “we”, the exclusive “we” pertains to such communicative situations, in which the speaker does not involve the addressee into the “communal we”, but emphasises the fact that the speaker and the group of people that the speaker represents are not the same as the addressee, i.e. the speaker is different from the audience. Starmer’s use of the exclusive “we” is evident from the corpus, in which nearly all of the instances of “we” are exclusive.

METAPHOR IN UKRAINIAN TERMINOLOGY OF EU SECONDARY LAW

Liana Goletiani — Wed, 31 Dec 2025 00:00:00 +0200

Background. Some English-language terms of EU secondary law have metaphorical components. Their translation causes difficulties if such a metaphor does not exist in the language of translation, or if it exists but is not used as a term. In this field of special translation, the problem of metaphor transfer has not yet been addressed. The study offers a comparative analysis of the equivalents of metaphorical terms on the material of Ukrainian translations and official EU acts drafted in other languages.

Purpose:

1) To establish equivalents of metaphorical terms of EU secondary law in different languages;

2) To distinguish convergent and divergent methods of translation;

3) To determine the influence of metaphor on the emergence of terminological variability;

4) To increase interest in metaphor in legal terminology from the scientific community.

Methods. The research is conducted using the comparative method. Ukrainian terms used in translations of EU acts are compared with their counterparts, primarily in English, which is the working language of the EU, as well as in Italian, German, Polish, Slovak, and other languages. The comparative method is also used in the intralinguistic perspective: in the case of the coexistence of more than one counterpart in the Ukrainian language, a comparative analysis is conducted at the level of definitions and usage, including in the micro-diachronic aspect. The procedures of translation analysis and structural-semantic analysis are used.

Results. It is shown that compliance with the principle of multilingual concordance of EU terminology is often not possible due to the presence, on the one hand, of metaphorical terms in the English version of EU law and the absence, on the other hand, of their full equivalents in other languages. When searching for a successful equivalent, Ukrainian translators make different translation decisions: 1) preservation of the metaphor; 2) replacement with another metaphor; 3) demetaphorization; 4) additional metaphorization occur. In addition, direct borrowings, hybrid terms, and explanatory terms were recorded among the equivalents in the material of different languages. In the micro-diachronic perspective, significant variability in Ukrainian terminology was revealed.

Discussion.The translation of a metaphor in the field of law is a multifactorial decision process. The cognitive and culturally-determined patterns that can correlate with the translation methods identified in the article, require in-depth study. Metaphorical terminology should find a more significant place in the terminological verification during the Ukrainian translation of EU acts and be based on scientifically sound and standardized principles.