?
Spot the Bot: Coarse-Grained Partition of Semantic Paths for Bots and Humans
P. 348–355.
Nowadays, technology is rapidly advancing: bots are writing comments, articles, and reviews. Due to this fact, it is crucial to know if the text was written by a human or by a bot. This paper focuses on comparing structures of the coarse-grained partitions of semantic paths for human-written and bot-generated texts. We compare the clusterizations of datasets of n-grams from literary texts and texts generated by several bots. The hypothesis is that the structures and clusterizations are different. Our research supports the hypothesis. As the semantic structure may be different for different languages, we investigate Russian, English, German, and Vietnamese languages.
M.: Max press, 2026.
The volume includes 64 papers from the international conference on computational linguistics and intelligent technologies 'Dialogue 2026,' representing a broad spectrum of theoretical and applied research in the field of natural language description, language process modeling, and the development of practically applicable computational linguistic technologies.
For specialists in theoretical and applied linguistics and intelligent technologies. ...
Added: June 27, 2026
Association for Computational Linguistics, 2024.
Added: June 14, 2026
Association for Computational Linguistics, 2026.
Added: June 13, 2026
Behzadidoost R., Neurocomputing 2025 Vol. 665 P. 1–21
While earlier research has focused on detecting misinformation content, identifying the users who spread it, referred to in this paper as fake information spreaders, remains a relatively new challenge. These users deliberately mix true and false information, making detection more difficult. This paper proposes a textual fingerprint learning model to detect fake information spreaders. The ...
Added: March 12, 2026
Karpov I., Kirillovich A., Goncharova E. et al., Plos One 2026 Vol. 21 No. 1 Article e0339468
Large language models (LLMs) offer significant potential for constructing commonsense knowledge graphs from text, demonstrating adaptability across diverse domains. However, their effectiveness varies significantly with domain-specific language, highlighting a critical need for specialized benchmarks to assess and optimize knowledge graph construction sub-tasks like named entity recognition, relation extraction, and entity linking. Currently, domain-specific benchmarks are ...
Added: January 15, 2026
Washington, United States of America: AAAI Press, 2025.
AAAI-25 Technical Tracks 23 (Natural Language Processing II) collects peer-reviewed research papers that advance the state of natural language processing, with an emphasis on large language models, efficient inference, instruction following, retrieval augmentation, and multimodal language understanding. The papers address both theoretical and practical challenges, including model efficiency, interactive generation, grounding in external knowledge and ...
Added: December 18, 2025
Kudelya A., Shirnin A., , in: Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025).: Association for Computational Linguistics, 2025. P. 1528–1533.
This paper describes LIBU (LoRA enhanced influence-based unlearning), an algorithm to solve the task of unlearning - removing specific knowledge from a large language model without retraining from scratch and compromising its overall utility (SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models). The algorithm combines classical influence functions to remove the influence of ...
Added: November 17, 2025
Morozov L., Mogilevskii A., Shirnin A., , in: Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025).: Association for Computational Linguistics, 2025. P. 2000–2007.
This paper describes LIBU (LoRA enhanced influence-based unlearning), an algorithm to solve the task of unlearning - removing specific knowledge from a large language model without retraining from scratch and compromising its overall utility (SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models). The algorithm combines classical influence functions to remove the influence of ...
Added: November 17, 2025
Association for Computational Linguistics, 2025.
Added: November 17, 2025
Association for Computational Linguistics, 2025.
The book contains this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first workshop, which had 14 accepted papers. As the field ...
Added: November 16, 2025
Anton R., Mikhalchuk M., Rahmatullaev T. et al., , in: Findings of the Association for Computational Linguistics: NAACL 2025.: Association for Computational Linguistics, 2025. P. 7757–7764.
We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation) carry surprisingly high context. Notably, removing these tokens — especially stopwords, articles, and commas — consistently degrades performance on MMLU and BABILong-4k, even if removing only irrelevant tokens. Our analysis ...
Added: November 6, 2025
Association for Computational Linguistics, 2025.
Added: November 6, 2025
Parakal E. G., Kuznetsov S., Makarov I. et al., IEEE Access 2025 Vol. 13 P. 149657–149678
This paper proposes a novel explainable document classification framework that integrates Concept Whitening (CW) with graph concepts that are derived from stable graph patterns, and extracted via methods based on Formal Concept Analysis (FCA) and pattern structures. Document graphs are constructed using Abstract Meaning Representation (AMR) graphs, from which graph concepts are extracted and aligned ...
Added: October 22, 2025
Krasnozhenov G., Lebedev S., В кн.: Московский транспорт. Наука и проектирование.Вып. 3.: М.: [б.и.], 2025. С. 56–74.
Статья посвящена анализу существующих трендов и вытекающих из направления развития интеллектуальных технологий актуальных задач для организаций, осуществляющих в Российской Федерации переход на цифровое проектирование. ...
Added: October 21, 2025
Shumen: INCOMA Ltd, 2025.
This paper introduces a rule-based lemmatization and word embedding pipeline for the endangered Bartangi language, part of the Pamiri language group. The system combines a manually constructed lemma dictionary with morphological suffix rules to improve linguistic consistency in low-resource settings. The results demonstrate enhanced lemmatization accuracy and higher-quality embeddings for downstream NLP tasks. The work ...
Added: October 20, 2025
Полехина А. А., Гусева А. Д., Деньги и кредит 2025 № 3 С. 28–62
Статья посвящена созданию индекса восприятия Банка России в Telegram-каналах, который может выступать как опережающий индикатор доверия населения к регулятору (корреляция с опросными данными «инФОМ» – 74%). Индекс оценивается на неструктурированных данных из 1400 Telegram-каналов. Это первый подобный индекс, который рисует объемную картину информационного поля, разделяя каналы по типам и ключевым сферам деятельности Банка России – ...
Added: October 14, 2025
Voevodina E., Современная зарубежная психология 2025 Т. 14 № 3 С. 172–181
Context and relevance. Well-being research faces methodological limitations of conventional psychometric measures, criticized for poor ecological validity, limited information yield, and inadequate capture of multidimensional construct of well-being. Advanced natural language processing (NLP) technologies offer solutions to these constraints. Objective. To evaluate opportunities and challenges of transformer-based NLP for well-being research. Methods and materials. We conducted an analytical review of ...
Added: October 9, 2025
Moiseev N., Абрамов И. А., Камакин А. Ю., В кн.: Параллельные вычислительные технологии – XIX всероссийская конференция с международным участием, ПаВТ'2025, г. Москва, 8–10 апреля 2025 г. Короткие статьи и описания плакатов.: Челябинск: Издательский центр ЮУрГУ, 2025. С. 301–301.
In recent years, with the advancement of deep learning and neural network methods, their application in geospatial analysis tasks has become particularly relevant. A key challenge in this field is assessing the state of urban infrastructure, including the classification of buildings by their functional purpose (residential, commercial, governmental, industrial). The use of neural networks significantly ...
Added: September 17, 2025