?
Word embedding in form of symmetric and skew-symmetric operator
Ch. 8. P. 54–59.
Кощенко Е. В., Kuralenok I.
Abstract—Existing word embedding models represent each word with two real-valued vectors: central and context. This happens because of words relations asymmetric nature and requires more time and data for training. We introduce a new approach based on asymmetric relations that uses the advantages of global vectors model. Due to the reduction of asymmetric information impact on resulting words representations, our model converges faster and outperforms existing models on words analogies tasks.
In book
Vol. 2372. , St. Petersburg: ООО "Цифровая фабрика "Быстрый Цвет", 2019.
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
Skorinkin D., Orekhov B., , in: The Oxford Handbook of Global Realisms.: Oxford: Oxford University Press, 2025. Ch. 10 P. 177–204.
This chapter investigates literary prose of the realist era in Russia using digital humanities methods. It focuses on how computational analysis can enhance an understanding of descriptions of literary characters, geographical locations, and lexical composition in literary texts. Using a corpus of more than five hundred texts (forty-six million word occurrences), it eschews the focus ...
Added: September 14, 2025
Zhang D., Jiang T., Васильев В. И. et al., Journal of Computational and Applied Mathematics 2026 Vol. 474 Article 116964
With the development of the applied discipline of commutative quaternions, the commutative quaternion equality constrained least squares (CQLSE) problem is gaining more and more attention as an effective tool. However, the knowledge gap in numerous CQLSE problems is now unresolved. This paper, by means of the complex representation matrix of a commutative quaternion matrix, first ...
Added: December 16, 2024
Sergei Koltcov, Surkov A., Filippov V. et al., PeerJ Computer Science 2024 Vol. 10 P. 41
Topic modeling is a widely used instrument for the analysis of large text collections.
In the last few years, neural topic models and models with word embeddings have
been proposed to increase the quality of topic solutions. However, these models
were not extensively tested in terms of stability and interpretability. Moreover, the
question of selecting the number of topics ...
Added: February 16, 2024
Sosnin A., Balakina Y. V., Кащихин А. Н., Вестник Санкт-Петербургского университета. Язык и литература 2022 Т. 19 № 1 С. 125–148
The article evaluates the quality of translation; we consider the applied and pragmatic aspects
of such evaluation in the conditions of the current rapid increase in the number of texts to be
translated. The article summarizes a plethora of assessment principles, each having its merits
and drawbacks, and examines the correlation between the categories of adequacy and equivalence
as ...
Added: May 31, 2022
Samenko I., Tikhonov A., Yamshchikov I. P., , in: Modern Management based on Big Data II and Machine Learning and Intelligent Systems IIIVol. 341.: IOS Press Ebooks, 2021. P. 502–510.
This paper shows that modern word embeddings contain information that distinguishes synonyms and antonyms despite small cosine similarities between corresponding vectors. This information is implicitly encoded in the geometry of the embeddings and could be extracted with a straightforward manifold learning procedure or a contrasting map. Such a map is trained on a small labeled ...
Added: December 2, 2021
Chistova E., Shelmanov A., Pisarevskaya D. et al., , in: Analysis of Images, Social Networks and Texts: 9th International Conference, AIST 2020, Skolkovo, Moscow, Russia, October 15–16, 2020, Revised Selected PapersVol. 12602.: Springer, 2021. P. 105–119.
This work presents the first fully-fledged discourse parser for
Russian based on the Rhetorical Structure Theory of Mann and Thompson
(1988). For the segmentation, discourse tree construction, and discourse
relation classification we employ deep learning models. With the
help of multiple word embedding techniques, the new state of the art
for discourse segmentation of Russian texts is achieved. We found ...
Added: November 17, 2021
Kuznetsov S., Goncharova E., , in: Proceedings of the Fifth International Scientific Conference "Intelligent Information Technologies for Industry" (IITI'21)Vol. 330.: Springer, 2022. P. 410–420.
Added: October 28, 2021
Bogomolov E., Golubev Y., Lobanov A. et al., , in: ASE '20: Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering.: ACM, 2020. P. 1316–1320.
Added: October 26, 2021
Yamshchikov I. P., Shibaev V., Tikhonov A., , in: Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP 2019.: Association for Computational Linguistics, 2019. P. 90–94.
This paper explores modern word embeddings in the context of sound symbolism. Using basic properties of the representations space one can construct semantic axes. A method is proposed to measure if the presence of individual sounds in a given word shifts its semantics along a specific axis. It is shown that, in accordance with several experimental ...
Added: April 7, 2021
Ryabinin M., Sergei Popov, Liudmila Prokhorenkova et al., , in: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).: Association for Computational Linguistics, 2020. P. 7317–7331.
It has become a de-facto standard to represent words as elements of a vector space (word2vec, GloVe). While this approach is convenient, it is unnatural for language: words form a graph with a latent hierarchical structure, and this structure has to be revealed and encoded by word embeddings. We introduce Graph-Glove: unsupervised graph word representations ...
Added: January 14, 2021
Bakarov A., Gureenkova O., Lecture Notes in Computer Science 2018 P. 16–21
This study considers the problem of automated detection of non-relevant posts on Web forums and discusses the approach of resolving this problem by approximation it with the task of detection of semantic relatedness between the given post and the opening post of the forum discussion thread. The approximated task could be resolved through learning the ...
Added: December 12, 2020
Bakarov A., PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE COMPUTATIONAL LINGUISTICS IN BULGARIA (CLIB '18) 2018 P. 153–161
Swivel (Submatrix-WIse Vector Embedding Learner) is a distributional semantic model based on counting point-wise mutual information values, capable of capturing word-context co-occurrences in the PMI matrix that were not noted in the training corpus. This model outperforms mainstream word embedding training algorithms such as Continuous Bag-of-Words, GloVe and Skip-Gram in word similarity and word analogy ...
Added: December 12, 2020
Smetanin S., Komarov M. M., , in: 2019 IEEE 21st Conference on Business Informatics (CBI)Vol. 2.: The Institute of Electrical and Electronics Engineers, Inc. , 2019. P. 482–486.
Nowadays, product reviews on e-commerce sites tend to be a valuable resource in terms of evaluation of customers’ behavior, their preferences, and needs. This paper provides an approach for sentiment analysis of product reviews in Russian using convolutional neural networks. We use Word2Vec pre-trained vectors as inputs for neural networks. This approach utilizes no hand-crafted ...
Added: November 1, 2020