<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">lingngu</journal-id><journal-title-group><journal-title xml:lang="ru">Вестник НГУ. Серия: Лингвистика и межкультурная коммуникация</journal-title><trans-title-group xml:lang="en"><trans-title>NSU Vestnik. Series: Linguistics and Intercultural Communication</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1818-7935</issn><publisher><publisher-name>Новосибирский государственный университет</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.25205/1818-7935-2023-21-1-67-82</article-id><article-id custom-type="elpub" pub-id-type="custom">lingngu-520</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>КОМПЬЮТЕРНАЯ И ПРИКЛАДНАЯ ЛИНГВИСТИКА</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>COMPUTER AND APPLIED LINGUISTICS</subject></subj-group></article-categories><title-group><article-title>Высокоуровневая семантическая интерпретация структуры статических моделей для русского языка</article-title><trans-title-group xml:lang="en"><trans-title>High-Level Semantic Interpretation of the Russian Static Models Structure</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-3746-2642</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Сериков</surname><given-names>О. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Serikov</surname><given-names>O. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Сериков Олег Алексеевич, исследователь, Школа Лингвистики НИУ ВШЭ; МФТИ; Институт искусственного интеллекта AIRI; Лаборатория исследования и сохранения малых языков ИЯЗ РАН</p><p>Москва</p></bio><bio xml:lang="en"><p>Oleg A. Serikov, researcher at HSE University; MIPT; AIRI; Laboratory for Study and Preservation of Minority Languages of the Institute of Linguistics RAS</p><p>Moscow</p></bio><email xlink:type="simple">srkvoa@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-4020-488X</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Ганеева</surname><given-names>В. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Geneeva</surname><given-names>V. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ганеева Вероника Александровна, магистрант</p><p>Москва</p></bio><bio xml:lang="en"><p>Veronika A. Geneeva, master student </p><p>Moscow</p></bio><email xlink:type="simple">vaganeeva@edu.hse.ru</email><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Аксенова</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Aksenova</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Аксенова Анна Александровна, исследователь данных</p><p>Москва</p></bio><bio xml:lang="en"><p>Anna A. Aksenova, data analyst</p><p>Moscow</p></bio><email xlink:type="simple">aaaksenova2@gmail.com</email><xref ref-type="aff" rid="aff-3"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-9569-9197</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Клышинский</surname><given-names>Э. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Klyshinskiy</surname><given-names>E. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Клышинский Эдуард Станиславович, доцент, канд. тех. наук</p><p>Москва</p></bio><bio xml:lang="en"><p>Eduard S. Klyshinskiy, Assoc. Prof., PhD in CS, researcher </p><p>Moscow</p></bio><email xlink:type="simple">eklyshinsky@hse.ru</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Московский физико-технический институт; Институт искусственного интеллекта AIRI; Институт языкознания РАН; Научно-исследовательский университет «Высшая школа экономики»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Moscow Institute of Physics and Technology; Artificial Intelligence Research Institute; Institute of Linguistics RAS; HSE University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Научно-исследовательский университет «Высшая школа экономики»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>HSE University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-3"><aff xml:lang="ru"><institution>ПАО «Сбербанк»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>JSC Sberbank</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2023</year></pub-date><pub-date pub-type="epub"><day>30</day><month>05</month><year>2023</year></pub-date><volume>21</volume><issue>1</issue><fpage>67</fpage><lpage>82</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Сериков О.А., Ганеева В.А., Аксенова А.А., Клышинский Э.С., 2023</copyright-statement><copyright-year>2023</copyright-year><copyright-holder xml:lang="ru">Сериков О.А., Ганеева В.А., Аксенова А.А., Клышинский Э.С.</copyright-holder><copyright-holder xml:lang="en">Serikov O.A., Geneeva V.A., Aksenova A.A., Klyshinskiy E.S.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://lingngu.elpub.ru/jour/article/view/520">https://lingngu.elpub.ru/jour/article/view/520</self-uri><abstract><p>С момента своего появления векторное пространство Word2vec стало универсальным инструментом для научной и практической деятельности. С течением времени стало понятно, что необходима разработка новых методов интерпретации расположения слов в векторном пространстве. Существующие методы включали рассмотрение узкого круга аналогий либо кластеризацию пространства. В последние годы активно развивается подход на основе пробинга – анализа влияния небольших изменений в модели на результат. В этой работе мы предлагаем метод интерпретации расположения слов в векторном пространстве, применимый ко всему пространству в целом. Метод позволяет выявлять основные направления, вдоль которых выделяются наиболее крупные группы слов (около трети всех слов словаря), противопоставляемые друг другу по некоторым семантическим признакам, а также строить неглубокую иерархию таких признаков. Эксперименты были проведены на трех моделях, обученных на разных корпусах: Национальном корпусе русского языка, Araneum Russicum и коллекции научных статей из разных предметных областей. Для экспериментов использовались только имена существительные, входящие в словарь моделей. Рассмотрена экспертная интерпретация подобного разделения вплоть до третьего уровня. Набор и иерархия этих признаков отличаются для разных моделей, однако все они являются достаточно общими. Было обнаружено, что выделенные признаки разделения зависят от состава корпусов, на которых проводилось обучение моделей, их направленности и стиля. Полученное разделение не всегда коррелирует с принятым в области разработки онтологий. Так, совпадающим признаком является абстрактность или вещность объекта. Однако для моделей на верхнем уровне оказывается более важным разделение на повседневную/специальную лексику, архаичную лексику, разделение на имена собственные и нарицательные. В статье приведены примеры слов, входящих в полученные группы.</p></abstract><trans-abstract xml:lang="en"><p>Since its inception, the Word2vec vector space has become a universal tool both for scientific and practical activities. Over time, it became clear that there is a lack of new methods for interpreting the location of words in vector spaces. The existing methods included consideration of analogies or clustering of a vector space. In recent years, an approach based on probing—analysis of the impact of small changes in the model on the result—has been actively developed. In this paper, we propose a new method for interpreting the arrangement of words in a vector space, applicable for the high-level interpretation of the entire space as a whole. The method provides for identifying the main directions which are selecting large groups of words (about a third of all the words in the model’s dictionary) and opposing them by some semantic features. The method allows us to build a shallow hierarchy of such features. We conducted our experiments on three models trained in different corpora: Russian National Corpus, Araneum Russicum and a collection of scientific articles from different subject domains. For our experiments, we used only nouns from the models’ dictionaries. The article considers an expert interpretation of such division up to the third level. The set of selected features and their hierarchy differ from model to model, but they have a lot in common. We have found that the identified semantic features depend on the texts comprising a corpus used for the model training, their subject domain, and style. The resulting division of words does not always correlate with the common sense used for ontology development. For example, one of the coinciding features is the abstract or material nature of the object. However, at the upper level of models, words are divided into everyday/special lexis, archaic lexis, proper names and common nouns. The article provides examples of words included in the derived groups.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>векторные модели</kwd><kwd>интерпретация модели</kwd><kwd>Word2vec</kwd><kwd>сингулярное разложение</kwd><kwd>построение онтологий</kwd></kwd-group><kwd-group xml:lang="en"><kwd>vector models</kwd><kwd>interpretation of models</kwd><kwd>Word2vec</kwd><kwd>singular vector decomposition</kwd><kwd>ontology development</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Авторы глубоко признательны Екатерине Владимировне Рахилиной за вдохновение, которое она дарила нам по мере написания этой статьи.</funding-statement><funding-statement xml:lang="en">The authors are extremely grateful to Ekaterina V. Rakhilina for her support and inspiration all the way along the process</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Грибова В. В., Петряева М. В., Окунь Д. Б., Шалфеева Е. А. Онтология медицинской диагностики для интеллектуальных систем поддержки принятия решений // Онтология проектирования. 2018. Т. 8, № 1(27). С. 58–73.</mixed-citation><mixed-citation xml:lang="en">Gribova, V. V., Petryaeva, M. V., Okun, D. B., Shalfeeva, E. A. Medical Diagnosis Ontology for Intelligent Decision Support Systems. Ontologiya Proektirovaniya [Ontology of designing], 2018, vol. 8, no. 1(27), pp. 58–73. (in Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Розенталь Д. Э., Теленкова М. А. Словарь-справочник лингвистических терминов. 2-е изд. М.: Просвещение, 1976, 543 с.</mixed-citation><mixed-citation xml:lang="en">Rozental, D. E., Telenkova, M. A. Dictionary of Linguistic Terms [Slovar-Spravochnik Lingvisticheskikh Terminov]. 2nd ed. Moscow: Prosveschenie, 1976, 543 p. (in Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Adi Y. et al. Fine-grained analysis of sentence embeddings using auxiliary prediction tasks [Электронный ресурс]. URL: https://arxiv.org/abs/1608.04207 (дата обращения 01.09.2022).</mixed-citation><mixed-citation xml:lang="en">Adi, Y. et al. Fine-grained analysis of sentence embeddings using auxiliary prediction tasks [Online]. 2016 URL: https://arxiv.org/abs/1608.04207 (accessed on 01.09.2022).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Bocharov V., Bichineva S., Granovsky D., Ostapuk N., Stepanova M. Quality assurance tools in the OpenCorpora project // Компьютерная лингвистика и интеллектуальные технологии: По материалам ежегодной Международной конференции «Диалог» (Бекасово, 25–29 мая 2011 г.). Вып. 10(17). М.: РГГУ, 2011. С. 107–115.</mixed-citation><mixed-citation xml:lang="en">Bocharov, V., Bichineva, S., Granovsky, D., Ostapuk, N., Stepanova, M. Quality assurance tools in the OpenCorpora project. In: Proc. of Computational Linguistics and Intellectual Technologies: Proceedings of the International Conference “Dialogue 2011”. Moscow: RSUH, 2011, pp. 107-115</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Bodenreider, O. The Unified Medical Language System (UMLS): integrating biomedical terminology [Электронный ресурс]. Oxford University Press, 2004, рр. 267–270. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC308795/ (дата обращения: 01.09.2022)</mixed-citation><mixed-citation xml:lang="en">Bodenreider, O. The Unified Medical Language System (UMLS): integrating biomedical terminology [Online]. Oxford University Press, 2004, рр. 267–270. URL: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC308795/ (accessed on: 01.09.2022)</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Chizhikova A., Murzakhmetov S., Serikov O., Shavrina T., Burtsev M. Attention Understands Semantic Relations // Proc. of the 13th Conference on Language Resources and Evaluation (LREC 2022), 2022, pp. 4040–4050.</mixed-citation><mixed-citation xml:lang="en">Chizhikova, A., Murzakhmetov, S., Serikov, O., Shavrina, T., Burtsev, M. Attention Understands Semantic Relations. In: Proc. of the 13th Conference on Language Resources and Evaluation (LREC-2022), 2022, pp. 4040–4050.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Conneau A., Lample G., Ranzato M. A., Denoyer L., Jégou H. Word Translation Without Parallel Data. [Электронный ресурс]. URL: https://arxiv.org/abs/1710.04087 (дата обращения: 01.09.2022).</mixed-citation><mixed-citation xml:lang="en">Conneau, A., Lample, G., Ranzato, M. A., Denoyer, L., Jégou, H. Word Translation Without Parallel Data [Online]. URL: https://arxiv.org/abs/1710.04087 (accessed on: 01.09.2022).</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Conneau A. et al. What you can cram into a single vector: Probing sentence embeddings for linguistic properties [Электронный ресурс]. URL: https://arxiv.org/abs/1805.01070 (дата обращения: 01.09.2022).</mixed-citation><mixed-citation xml:lang="en">Conneau, A. et al. What you can cram into a single vector: Probing sentence embeddings for linguistic properties [Online]. URL: https://arxiv.org/abs/1805.01070 (accessed on: 01.09.2022).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Ethayarajh K. How contextual are contextualized word representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings // Proc. of Association for Computational Linguistics, Hong Kong, 2019, pp. 55–65.</mixed-citation><mixed-citation xml:lang="en">Ethayarajh, K. How contextual are contextualized word representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings. In Proc. of Association for Computational Linguistics, Hong Kong, 2019, pp. 55–65.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Faruqui M., Tsvetkov Y., Yogatama D., Dyer C., Smith N. A. Sparse Overcomplete Word Vector Representations // Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, 2015, pp. 1491–1500.</mixed-citation><mixed-citation xml:lang="en">Faruqui, M., Tsvetkov, Y., Yogatama, D., Dyer, C., Smith, N. A. Sparse Overcomplete Word Vector Representations. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, 2015, pp. 1491–1500.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Gallant S. Context vector representations for document retrieval // Proc. of AAAI Workshop on Natural Language Text Retrieval, 1991.</mixed-citation><mixed-citation xml:lang="en">Gallant, S. Context vector representations for document retrieval. In: Proc. of AAAI Workshop on Natural Language Text Retrieval, 1991.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Gustaf S. Meaning and change of meaning: with special reference to the English language. Indiana University Press, 1964, 490 p.</mixed-citation><mixed-citation xml:lang="en">Gustaf, S. Meaning and change of meaning: with special reference to the English language. Indiana University Press, 1964, 490 p.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Korogodina, O., Karpik, O., Klyshinsky E. Evaluation of Vector Transformations for Russian Word2Vec and FastText Embeddings // Proc. of Graphicon-2020. DOI 10.51130/graphicon-2020-2-3-18</mixed-citation><mixed-citation xml:lang="en">Korogodina , O., Karpik, O., Klyshinsky E. Evaluation of Vector Transformations for Russian Word2Vec and FastText Embeddings. In: Proc. of Graphicon 2020. DOI 10.51130/graphicon-2020-2-3-18</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Kozlowski A., Taddy М., Evansa J. The Geometry of Culture: Analyzing the Meanings of Class through Word Embeddings // American Sociological Review. 2017. Pp. 905–949.</mixed-citation><mixed-citation xml:lang="en">Kozlowski, A., Taddy, М., Evansa, J. The Geometry of Culture: Analyzing the Meanings of Class through Word Embeddings. American Sociological Review, 2017, pp. 905–949.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Kutuzov A. Distributional word embeddings in modeling diachronic semantic change [Электронный ресурс] / Doctoral Thesis, University of Oslo, 2020. https://www.duo.uio.no/bitstream/handle/10852/81045/1/Kutuzov-Thesis.pdf.</mixed-citation><mixed-citation xml:lang="en">Kutuzov, A. Distributional word embeddings in modeling diachronic semantic change [Online]. Doctoral Thesis, University of Oslo, 2020. URL: https://www.duo.uio.no/bitstream/handle/10852/81045/1/Kutuzov-Thesis.pdf.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Lasri K., Pimentel T., Lenci A., Poibeau T., Cotterell R. Probing for the Usage of Grammatical Number // Proc. of the 60th Annual Meeting of the Association for Computational Linguistics. 2022. Vol. 1, Pp. 8818–8831.</mixed-citation><mixed-citation xml:lang="en">Lasri, K., Pimentel, T., Lenci, A., Poibeau, T., Cotterell, R. Probing for the Usage of Grammatical Number. In: Proc. of the 60th Annual Meeting of the Association for Computational Linguistics, vol. 1, 2022, pp. 8818–8831.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Linzen T., Dupoux E., Goldberg Y. Assessing the ability of LSTMs to learn syntax-sensitive dependencies // Transactions of the Association for Computational Linguistics. 2016. Vol. 4. Pp. 521–535.</mixed-citation><mixed-citation xml:lang="en">Linzen, T., Dupoux, E., Goldberg, Y. Assessing the ability of LSTMs to learn syntax-sensitive dependencies. Transactions of the Association for Computational Linguistics, 2016, vol. 4, pp. 521–535.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Loureiro D., Alipio M. J. Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation // Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019. Pp. 5682–5691.</mixed-citation><mixed-citation xml:lang="en">Loureiro, D., Alipio, M. J. Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019, pp. 5682–5691.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Representations. Virtual Event, Austria, May 3-7, 2021 [Электронный ресурс]. URL: https://openreview.net/forum?id=mNtmhaDkAr (дата обращения 01.09.2022)</mixed-citation><mixed-citation xml:lang="en">Representations. Virtual Event, Austria, May 3-7, 2021. URL: https://openreview.net/forum?id=mNtmhaDkAr (accessed on: 01.09.2022).</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Mikolov T., Chen K., Corrado G., Dean J. Efficient estimation of word representations in vector space // Proc. of International Conference on Learning Representations (ICLR), 2013 a.</mixed-citation><mixed-citation xml:lang="en">Mikolov, T., Chen, K., Corrado, G., Dean, J. Efficient estimation of word representations in vector space. Proc. of International Conference on Learning Representations (ICLR), 2013 a.</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Mikolov T., Chen K., Corrado G., Dean J. Distributed Representations of Words and Phrases and their Compositionality // Proc. of 27th Annual Conference on Neural Information Processing Systems. 2013. Pp. 3111–3119.</mixed-citation><mixed-citation xml:lang="en">Mikolov, T., Chen, K., Corrado, G., Dean, J. Distributed Representations of Words and Phrases and their Compositionality. In: Proc. of 27th Annual Conference on Neural Information Processing Systems, 2013, pp. 3111–3119.</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Rabinovich E., Xu Y., Stevenson S. The Typology of Polysemy: A Multilingual Distributional Framework, 2020 [Электронный ресурс]. URL: https://arxiv.org/abs/2006.01966v1 (дата обращения 01.09.2022).</mixed-citation><mixed-citation xml:lang="en">Rabinovich, E., Xu, Y., Stevenson, S. The Typology of Polysemy: A Multilingual Distributional Framework, 2020 [Online]. URL: https://arxiv.org/abs/2006.01966v1 (accessed on: 01.09.2022).</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Ravfogel S. et al. Counterfactual interventions reveal the causal effect of relative clause representations on agreement prediction [Электронный ресурс]. URL: https://arxiv.org/abs/2105.06965 (дата обращения 01.09.2022).</mixed-citation><mixed-citation xml:lang="en">Ravfogel, S. et al. Counterfactual interventions reveal the causal effect of relative clause representations on agreement prediction [Online]. URL: https://arxiv.org/abs/2105.06965 (accessed on: 01.09.2022).</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Rubinstein D., Levi E., Schwartz R., Rappoport A. How well do distributional models capture different types of semantic knowledge? [Электронный ресурс] // Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Association for Computational Linguistics. 2015. Pp. 726–730. https://aclanthology.org/P15-2119.pdf.</mixed-citation><mixed-citation xml:lang="en">Rubinstein, D., Levi, E., Schwartz, R., Rappoport, A. How well do distributional models capture different types of semantic knowledge? In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, 2015, pp. 726–730. https://aclanthology.org/P15-2119.pdf.</mixed-citation></citation-alternatives></ref><ref id="cit25"><label>25</label><citation-alternatives><mixed-citation xml:lang="ru">Subramanian A., Pruthi D., Jhamtani H., Berg-Kirkpatrick T., Hovy E. SPINE: SParse Interpretable Neural Embeddings // The 32nd AAAI Conference on Artificial Intelligence (AAAI-18), 2018.</mixed-citation><mixed-citation xml:lang="en">Subramanian, A., Pruthi, D., Jhamtani, H., Berg-Kirkpatrick, T., Hovy, E. SPINE: SParse Interpretable Neural Embeddings. The 32nd AAAI Conference on Artificial Intelligence (AAAI-18), 2018.</mixed-citation></citation-alternatives></ref><ref id="cit26"><label>26</label><citation-alternatives><mixed-citation xml:lang="ru">Tenney I., Das D., Pavlick E. BERT rediscovers the classical NLP pipeline. [Электронный ресурс].</mixed-citation><mixed-citation xml:lang="en">Tenney, I., Das, D., Pavlick, E. BERT rediscovers the classical NLP pipeline [Online]. URL: https:// arxiv.org/abs/1905.05950 (accessed on: 01.09.2022).</mixed-citation></citation-alternatives></ref><ref id="cit27"><label>27</label><citation-alternatives><mixed-citation xml:lang="ru">URL: https://arxiv.org/abs/1905.05950 (дата обращения 01.09.2022).</mixed-citation><mixed-citation xml:lang="en">Vig, J. et al. Causal mediation analysis for interpreting neural NLP: The case of gender bias [Online]. URL: https://arxiv.org/abs/2004.12265 (accessed on: 01.09.2022).</mixed-citation></citation-alternatives></ref><ref id="cit28"><label>28</label><citation-alternatives><mixed-citation xml:lang="ru">Vig J. et al. Causal mediation analysis for interpreting neural nlp: The case of gender bias [Электронный ресурс]. URL: https://arxiv.org/abs/2004.12265 (дата обращения 01.09.2022).</mixed-citation><mixed-citation xml:lang="en">Voloshina, E., Serikov, O., Shavrina, T. Is neural language acquisition similar to natural? A chronological probing study. In Proc. of Computational Linguistics and Intellectual Technologies: Proceedings of the International Conference “Dialogue 2022”. 2022. pp. 550-563</mixed-citation></citation-alternatives></ref><ref id="cit29"><label>29</label><citation-alternatives><mixed-citation xml:lang="ru">Voloshina E., Serikov O., Shavrina T. Is neural language acquisition similar to natural? A chronological probing study // Proc. of Computational Linguistics and Intellectual Technologies: Proceedings of the International Conference “Dialogue 2022”, 2022. Pp. 550–563.</mixed-citation><mixed-citation xml:lang="en">Weeds, J., Clarke, D., Reffin, J., Weir, D., Keller, B. Learning to distinguish hypernyms and co-hyponyms. In: Proceedings of COLING-2014. Dublin, the 25th International Conference on Computational Linguistics: Technical Papers, 2014, pp. 2249–2259.</mixed-citation></citation-alternatives></ref><ref id="cit30"><label>30</label><citation-alternatives><mixed-citation xml:lang="ru">Weeds J., Clarke D., Reffin J., Weir D., Keller B. Learning to distinguish hypernyms and cohyponyms // Proceedings of COLING 2014. Dublin, the 25th International Conference on Computational Linguistics: Technical Papers, 2014. Pp. 2249–2259.</mixed-citation><mixed-citation xml:lang="en">Yao, S., Yu, D., Xiao, K. Enhancing Domain Word Embedding via Latent Semantic Imputation, 2019 [Online]: arXiv:1905.08900v1. URL: https://arxiv.org/abs/1905.08900 (accessed on: 01.09.2022).</mixed-citation></citation-alternatives></ref><ref id="cit31"><label>31</label><citation-alternatives><mixed-citation xml:lang="ru">Yao S., Yu D., Xiao K. Enhancing Domain Word Embedding via Latent Semantic Imputation, 2019 [Электронный ресурс]. URL: https://arxiv.org/abs/1905.08900 (дата обращения 01.09.2022).</mixed-citation><mixed-citation xml:lang="en">Yao S., Yu D., Xiao K. Enhancing Domain Word Embedding via Latent Semantic Imputation, 2019 [Электронный ресурс]. URL: https://arxiv.org/abs/1905.08900 (дата обращения 01.09.2022).</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
