AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS最新文献_第7页

An Algorithm for Finding an Exact Solution to the Problem of Multiple Traveling Salesmen 多旅行推销员问题的精确解算法

IF 0.4

AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS Pub Date : 2026-08-10 DOI: 10.3103/S0005105526700330

O. A. Klimenko, B. Ya. Steinberg

引用次数: 0

An Ontological Model for Integrating Cognitive and Sociological Data for Personnel Assessment 一种整合认知与社会学数据的本体论模型用于人事评估

IF 0.4

AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS Pub Date : 2026-08-10 DOI: 10.3103/S0005105526700433

Y. A. Khalin, A. A. Ilina

引用次数: 0

Artificial Intelligence in a Few Fragments 几个片段中的人工智能

IF 0.4

AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS Pub Date : 2026-08-10 DOI: 10.3103/S0005105526700354

Yu. E. Polyak

引用次数: 0

The Place of Lisp in Teaching Functional Programming Lisp在函数式程序设计教学中的地位

IF 0.4

AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS Pub Date : 2026-08-10 DOI: 10.3103/S0005105526700378

B. L. Faifel, L. V. Gorodnyaya

引用次数: 0

Keldysh Institute of Applied Mathematics’ Preprints: Conversion from MS Word to HTML Keldysh应用数学研究所的预印本：从MS Word到HTML的转换

IF 0.4

AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS Pub Date : 2026-08-10 DOI: 10.3103/S0005105526700305

A. A. Vorobjov, R. Y. Skornyakova

引用次数: 0

Analysis of the Efficiency of Subword Tokenizers in a Low-Resource Linguistic Environment: Implementation Experience for the Tajik Language 低资源语言环境下子词标记器的效率分析：塔吉克语的实现经验

IF 0.4

AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS Pub Date : 2026-08-10 DOI: 10.3103/S0005105526700391

M. K. Arabov, S. S. Khaybullina

{"title":"Analysis of the Efficiency of Subword Tokenizers in a Low-Resource Linguistic Environment: Implementation Experience for the Tajik Language","authors":"M. K. Arabov, S. S. Khaybullina","doi":"10.3103/S0005105526700391","DOIUrl":"10.3103/S0005105526700391","url":null,"abstract":"<p>Contemporary approaches to subword text tokenization are considered in application to the low-resource Tajik language, which is characterised by a complex morphological structure and high variability of word forms. In the course of the study, a large-scale heterogeneous corpus was compiled and preprocessed, comprising 99 books and 134 497 textual articles of various genres and topics, with a total volume exceeding 33 million tokens. The corpus was cleaned of noise, normalised, and used as a basis for training and subsequent testing of subword models. On the basis of this corpus, five tokenization models were trained and analyzed, implementing the BPE, WordPiece, and Unigram algorithms using the Hugging Face Tokenizers and SentencePiece libraries. A comparative assessment was carried out according to a number of key indicators, including the out-of-vocabulary (OOV) rate, text compression ratio, tokenization speed, as well as n-gram distribution characteristics that make it possible to evaluate the ability of the models to reflect the morphological and structural organization of the language. The experimental results revealed the strengths and weaknesses of various approaches to subword segmentation and identified the most effective tokenization strategies under the conditions of the morphological complexity of the Tajik language. The findings may be used in the development of language models and applied NLP tools for Tajik and other low-resource languages, thus contributing to the expansion of their presence in the digital environment.</p>","PeriodicalId":42995,"journal":{"name":"AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS","volume":"60 2","pages":"S225 - S230"},"PeriodicalIF":0.4,"publicationDate":"2026-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148695111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Errors of Artificial Intelligence in Solving Combinatorial Problems 人工智能在解决组合问题中的错误

IF 0.4

AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS Pub Date : 2026-08-10 DOI: 10.3103/S0005105526700342

E. V. Krutenko, B. Y. Steinberg

引用次数: 0

Using Open Archives of Scaled Vertical Radiosondе Ionograms as Labeled Data for Training Machine Learning Models 使用开放档案的缩放垂直无线电测深图作为标记数据训练机器学习模型

IF 0.4

AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS Pub Date : 2026-08-10 DOI: 10.3103/S000510552670038X

A. O. Schiriy

引用次数: 0

VIT Quantization: CPU-Centric Analysis of the Trade-off between Size and Speed VIT量化：以cpu为中心的大小和速度之间权衡的分析

IF 0.5

AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS Pub Date : 2026-06-08 DOI: 10.3103/S0005105526700196

A. R. Nigmatullin, R. A. Lukmanov, A. Taha

{"title":"VIT Quantization: CPU-Centric Analysis of the Trade-off between Size and Speed","authors":"A. R. Nigmatullin, R. A. Lukmanov, A. Taha","doi":"10.3103/S0005105526700196","DOIUrl":"10.3103/S0005105526700196","url":null,"abstract":"<p>Using Vision Transformer (ViT) models in real medical practice such as, for example, in hospitals or diagnostic centers, is often difficult because doctors’ work computers usually do not have powerful graphics processors (GPUs), and computing resources are limited. This work investigates a complete practical pipeline for model inference, aimed at reducing computational costs without significant loss of predictive performance. The proposed approach combines several optimization techniques. First, knowledge distillation (KD) is used, where a compact student model learns to mimic the behavior of a larger, more accurate teacher model. Second, an exponential moving average (EMA) of the model weights is determined to stabilize training and improve generalization. Third, posttraining INT8 quantization (PTQ) is explored to reduce model size and accelerate inference. Additionally, a simplified quantization-aware training variant (QAT-lite) is considered, where the effects of quantization are partially incorporated during fine-tuning. Experiments are conducted on the ISIC dataset, which contains dermoscopic images of skin lesions. Model performance is evaluated using standard classification metrics, including accuracy, macroaveraged F1 score, and area under the ROC curve (ROC-AUC). CPU performance is also analyzed, including inference latency, throughput, memory consumption, and the final model size. The results show that posttraining INT8 quantization preserves performance close to the FP32 baseline while substantially reducing memory and computational requirements. In contrast, QAT-lite does not consistently provide reproducible improvements over PTQ.</p>","PeriodicalId":42995,"journal":{"name":"AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS","volume":"60 1","pages":"S102 - S110"},"PeriodicalIF":0.5,"publicationDate":"2026-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148193796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Role of Artificial Intelligence in Creation, Curation, and Interpretation of Digital Library Collections 人工智能在数字图书馆馆藏的创造、管理和解读中的作用

IF 0.5

AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS Pub Date : 2026-06-08 DOI: 10.3103/S0005105526700214

E. V. Samokhodkin, A. A. Elzon, E. G. Samokhodkina, D. V. Loshadkin

{"title":"The Role of Artificial Intelligence in Creation, Curation, and Interpretation of Digital Library Collections","authors":"E. V. Samokhodkin, A. A. Elzon, E. G. Samokhodkina, D. V. Loshadkin","doi":"10.3103/S0005105526700214","DOIUrl":"10.3103/S0005105526700214","url":null,"abstract":"<div><p>This study examines the role of artificial intelligence (AI) in reshaping the ecosystem of digital scholarly communication, drawing on evidence from electronic libraries and large-scale knowledge aggregators. On the basis of an integrative review of recent international and Russian-language scholarship, AI is found to be gradually evolving into a system-forming infrastructural mechanism across the life cycle of electronic collections, structuring processes of selection, digitization, metadata creation, storage, and service-oriented resource discovery and access. In parallel, intelligent recommender systems are substantiated as an epistemic mediator influencing the configuration of scholarly reading, the distribution of research attention, and the visibility of peripheral forms of knowledge within the spatial–linguistic architecture of science. It is demonstrated that algorithmic personalization cannot be reduced to improved search convenience; rather, it participates in constructing relevance norms, linguistic and regional hierarchies, and new regimes for interpreting collections. The effects identified make it possible to conceptualize algorithmic mediation at the intersection of the micro level of research identity and the macro level of the global distribution of scholarly knowledge, while also underscoring the need for reflexive governance of recommender loops to preserve epistemic diversity and enhance the transparency of libraries’ digital infrastructure.</p></div>","PeriodicalId":42995,"journal":{"name":"AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS","volume":"60 1","pages":"S117 - S124"},"PeriodicalIF":0.5,"publicationDate":"2026-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148193805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0