This paper presents a pipeline that converts unstructured interview transcripts into a semantically enriched, queryable knowledge resource. The texts from the Digitalne Ikone 20+ interview collection were first encoded in TEI XML (Text Encoding Initiative), marking interview boundaries, paragraph breaks, speaker turns with identifiers, dates, and topics. This structural encoding underpins downstream NLP and enables structured querying (e.g., by speaker). We then applied Named Entity Recognition to identify persons, places, organizations, and events, and embedded the results directly in TEI. In the third stage, Named Entity Linking mapped entity mentions to canonical Wikidata identifiers via context-aware disambiguation; missing entries were added to Wikidata when necessary. The resulting TEI+NER/NEL corpus, serialized as linked data, follows the NIF (NLP Interchange Framework). The pipeline also supports retrieval-augmented summarization that retrieves evidence passages and prompts LLMs (implemented with DSPy) to produce faithful interview summaries. We discuss design choices (TXM for textometry with JeRTeh resources; TESLA models for NER/NEL), report qualitative gains in interpretability through semantic links, and outline future work on domain-adapted NER/NEL, graph-based completion, and more expressive RAG architectures. The approach is replicable for other oral-history or media corpora and advances practical, evidence-grounded access to cultural archives and beyond.

LLMs capable of answering questions, fulfilling diverse user requests, and functioning as chatbots rely heavily on extensive datasets. However, for the Serbian language, there is a significant lack of high-quality datasets structured in a question-and-answer (QA) format. To address this, we extracted a portion of the SQuAD-sr dataset, which, to the best of our knowledge, is the largest QA dataset in Serbian and contains over 87k samples. While this dataset is an incredibly valuable resource, it was translated using an adapted Translate-Align-Retrieve method and contains errors and terminological inaccuracies. In this work, we systematically reviewed and corrected more than 7k samples from the SQuAD-sr dataset, significantly improving the dataset’s reliability and quality. We call this modified subset of the SQuAD-sr dataset, the SQuAD-sr-md dataset. The corrections that were made are crucial for training accurate and robust QA models in Serbian, ensuring that AI systems can leverage the full potential of this dataset. We also introduce an additional QA dataset generated from encyclopedia articles, Wikipedia pages, and scientific paper abstracts using LLMs, which contains 74k samples. We name this dataset the SerbianQA-Gen.

This study presents the Sentiment Analysis of the Serbian old novels from the 1840-1920 period, employing the Mistral Large Language Model (LLM) to pioneer zero and few-shot learning techniques. The main approach innovates by devising research prompts that include guidance text for zero-shot classification and examples for few-shot learning, enabling the LLM to classify sentiments into positive, negative, or objective categories. This methodology aims to streamline sentiment analysis by limiting responses, thereby enhancing classification precision. Python, along with the Hugging Face Transformers and LangChain libraries, serves as our technological backbone, facilitating the creation and refinement of research prompts tailored for sentence-level sentiment analysis. The results of sentiment analysis in both scenarios, zero-shot and few-shot, have indicated that the zero-shot approach outperforms, achieving an accuracy of 68.2%.

The paper presents the results of the research related to the preparation of parallel corpora, focusing on transformation into RDF graphs using NLP Interchange Format (NIF) for linguistic annotation. We give an overview of the parallel corpus that was used in this case study, as well as the process of POS tagging, lemmatization, named entity recognition (NER), and named entity linking (NEL), which is implemented using Wikidata. In the first phase of NEL main characters and places mentioned in novels are stored in Wikidata and in the second phase they are linked with the occurrences of previously annotated entities in text. Next, we describe the named entity linking (NEL), data conversion to RDF, and incorporation of NIF annotations. Produced NIF files were evaluated through the exploration of triplestore using SPARQL queries. Finally, the bridging of Linked Data and Digital Humanities research is discussed, as well as some drawbacks related to the verbosity of transformation. Semantic interoperability concept in the context of linked data and parallel corpora ensures that data exchanged between systems carries shared and well-defined meanings, enabling effective communication and understanding.

In this paper we present the Serbian part of the ELTeC multilingual corpus of novels written in the time period 1840-1920. The corpus is being built in order to test various distant reading methods and tools with the aim of re-thinking the European literary history. We present the various steps that led to the production of the Serbian sub-collection: the novel selection and retrieval, text preparation, structural annotation, POS-tagging, lemmatization and named entity recognition. The Serbian sub-collection was published on different platforms in order to make it freely available to various users. Several use examples show that this sub-collection is usefull for both close and distant reading approaches.

In this paper we present the wikification of the ELTeC (European Literary Text Collection), developed within the COST Action “Distant Reading for European Literary History” (CA16204). ELTeC is a multilingual corpus of novels written in the time period 1840—1920, built to apply distant reading methods and tools to explore the European literary history. We present the pipeline that led to the production of the linked dataset, the novels’ metadata retrieval and named entity recognition, transformation, mapping and Wikidata population, followed by named entity linking and export to NIF (NLP Interchange Format). The speeding up of the process of data preparation and import to Wikidata is presented on the use case of seven sub-collections of ELTeC (English, Portuguese, French, Slovenian, German, Hungarian and Serbian). Our goal was to automate the process of preparing and importing information, so OpenRefine and QuickStatements were chosen as the best options. The paper also includes examples of SPARQL queries for retrieval of authors, novel titles, publication places and other metadata with different visualisation options as well as statistical overviews.

The training of new tagger models for Serbian is primarily motivated by the enhancement of the existing tagset with the grammatical category of a gender. The harmonization of resources that were manually annotated within different projects over a long period of time was an important task, enabled by the development of tools that support partial automation. The supporting tools take into account different taggers and tagsets. This paper focuses on TreeTagger and spaCy taggers, and the annotation schema alignment between Serbian morphological dictionaries, MULTEXT-East and Universal Part-of-Speech tagset. The trained models will be used to publish the new version of the Corpus of Contemporary Serbian as well as the Serbian literary corpus. The performance of developed taggers were compared and the impact of training set size was investigated, which resulted in around 98% PoS-tagging precision per token for both new models. The sr_basic annotated dataset will also be published.