Ляшевская Ольга Николаевна

Russian Constructicon 2.0: New Features and New Perspectives of the Biggest Constructicon Ever Built

2023 · CHAPTER · en

Disambiguation in context in the Russian National Corpus: 20 yeas later

2023 · CHAPTER · en

An updated annotation of the Main, Media, and some other corpora of the Russian National Corpus (RNC) features the part-of-speech and other morphological information, lemmas, dependency structures, and constituency types. Transformer-based architectures are used to resolve the homonymy in context according to a schema based on the manually disambiguated subcorpus of the Main corpus (morphology and lexicon) and UD-SynTagRus (syntax). The paper discusses the challenges in applying the models to texts of different registers, orthographies, and time periods, on the one hand, and making the new version convenient for users accustomed to the old search practices, on the other. The re-annotated corpus data form the basis for the enhancement of the RNC tools such as word and n-gram frequency lists, collocations, corpus comparison, and Word at a glance.

From web to dialects: how to enhance non-standard Russian lects lemmatisation?

2023 · CHAPTER · en

The growing need for using small data distinguished by a set of distributional properties becomes all the more apparent in the era of large language models (LLM). In this paper, we show that for the lemmatisation of the web as corpora texts, heterogeneous social media texts, and dialect texts, the morphological tagging by a model trained on a small dataset with specific properties generally works better than the morphological tagging by a model trained on a large dataset. The material we use is Russian non-standard texts and interviews with dialect speakers. The sequence-to-sequence lemmatisation with the help of taggers trained on smaller linguistically aware datasets achieves the average results of 85 to 90 per cent. These results are consistently (but not always), by 1-2 per cent. higher than the results of lemmatisation with the help of the large-dataset-trained taggers. We analyse these results and outline the possible further research directions.

The Effect of (Historical) Language Variation on the East Slavic Lects Lemmatisers Performance

2023 · ARTICLE · en

The need to develop tools for historical and regional variations is becoming more urgent in natural language processing. In this paper, we present two candidate systems for lemmatising historical East Slavic lects (Late Old East Slavic and Middle Russian), as well as modern regional East Slavic lects (Belogornoje and Megra): BERT-based end-to-end pipeline with language-specific heuristics and sequence-to-sequence BART-based encoderdecoder. To evaluate their predictions, we use accuracy score and string similarity measures, such as Levenshtein distance. The BERT-based model is more suitable for the regional data, achieving 85% accuracy score, and only 74% on the historical data. BART-based model climbs up to 92.6% accuracy score on the historical data, yet gets only 80% on the regional data. We provide an error analysis and discuss ways to enhance models, such as dictionary lookup and spellchecker.

Automated Metaphor Identification in Russian and Its Implications for Metaphor Studies

2022 · CHAPTER · en

Sculpting enhanced dependencies for Belarusian

2022 · CHAPTER · en

Enhanced Universal Dependencies (EUD) are enhanced graphs expressed on top of basic dependency trees. EUD support repre- sentation of deeper syntactic relations in constructions such as coordi- nation, gapping, relative clauses, and argument sharing through control and raising. The paper presents experiments on the EUD parsing of the low-resource Belarusian language, for which no corpora with enhanced annotations were available. Models trained on the Universal Dependencies treebanks of two closely related Slavic languages, Russian and Ukrainian, were used to parse sen- tences translated from Belarusian. After that, EUD were projected to the original sentences, which gave us ELAS (Enhanced Labeled Attach- ment Score) 78.1% for both Russian and Ukrainian in evaluation. We also trained a model of one of the IWPT 2020 Shared Task participants on obtained the annotations in Belarusian and achieved ELAS 83.4%. The analysis shows that the most common mistakes of cross-lingual parsing are rooted in different theoretical perspectives and practice approaches to the annotation of particular types of clauses in the three Slavic treebanks. Russian and Ukrainian EUD transfer models tend to make mistakes when dealing with the predicate argument relations, which are hard to iden- tify without understanding the semantics of the sentence. The alignment method decreases the quality of the annotation by confusing tokens that occur in a sentence more than once.

Accuracy, syntactic complexity and task type at play in examination writing: A corpus-based study

2022 · CHAPTER · en

This chapter explores the association between syntactic complexity and syntactic accuracy in essays written by Russian learners of English in reply to two examination task types: a description of graphical material (Task 1) and an opinion essay (Task 2). A Poisson regression model served to predict the number of syntactic errors. Two syntactic complexity parameters were statistically significant in predicting syntactic accuracy in both tasks: the numbers of sentences and adverbial clauses. Three more parameters predicted the accuracy in Task 1 only: maximum depth of syntactic trees, and the numbers of adjective + noun and noun + infinitive constructions. Six parameters were related to syntactic accuracy in Task 2: the numbers of all clauses, of tokens and of T- units; the average length of sentence; and the numbers of coordinated and of participle + noun constructions.

Word-formation complexity: a learner corpus-based study

2022 · ARTICLE · en

В статье рассматривается словообразовательная сложность учебных текстов, которая трактуется как система измерений, показывающих разнообразие приемов словообразования разного уровня, от простых до продвинутых, используемых учащимся. Анализируется взаимосвязь между сложностью и ошибками, которые учащиеся допускают в словообразовании. Исследование основано на материалах REALEC - корпуса английских экзаменационных эссе, написанных студентами университета с родным русским языком. Предлагается подход к измерению словообразовательной сложности, основанный на классификации суффиксов Бауэра и Нейшена (Bauer & Nation 1993), и анализируется соответствие между показателями индексов сложности и количеством ошибок словообразования, размеченных в текстах корпуса, с учетом типа экзаменационного задания. Постулируется гипотеза о том, что с увеличением сложности количество ошибок должно уменьшаться, и проводится статистический анализ параметров сложности и безошибочности. В работе показано, во-первых, что использование словообразовательных суффиксов более высокой сложности связано с количеством ошибок в текстах. Во-вторых, разные уровни иерархии сложности оказывают разнонаправленное влияние на точность: в частности, использование нерегулярных словообразовательных моделей положительно связано с количеством ошибок. В-третьих, следует учитывать тип экзаменационного задания, в том числе ожидаемые формально-регистровые особенности текста. Гипотеза была подтверждена для регулярных, но нечастотных суффиксальных моделей при их использовании в описаниях рисунков и графиков - текстах, следующих определенному формату и включающих элементы академического письма. Однако в случае аргументативных эссе выдвинутая гипотеза требует уточнения.

Review of Practices of Collecting and Annotating Texts in the Learner Corpus REALEC

2022 · CHAPTER · en

REALEC, learner corpus released in the open access, had received 6,054 essays written in English by HSE undergraduate students in their English university-level examination by the year 2020. This paper reports on the data collection and manual annotation approaches for the texts of 2014–2019 and discusses the computer tools available for working with the corpus. This provides the basis for the ongoing development of automated annotation for the new portions of learner texts in the corpus. The observations in the first part were made on the reliability of the total of 134,608 error tags manually annotated across the texts in the corpus. Some examples are given in the paper to emphasize the role of the interference with learners’ L1 (Russian), one more direction of the future corpus research. A number of studies carried out by the research team working on the basis of the REALEC data are listed as examples of the research potential that the corpus has been providing

Constructing a Lexical Resource of Russian Derivational Morphology

2022 · CHAPTER · en

Words of any language are to some extent related thought the ways they are formed. For instance, the verb ‘exempl-ify’ and the noun ‘example-s’ are both based on the word ‘example’, but the verb is derived from it, while the noun is inflected. In Natural Language Processing of Russian, the inflection is satisfactorily processed; however, there are only a few machine-trackable resources that capture derivations even though Russian has both of these morphological processes very rich. Therefore, we devote this paper to improving one of the methods of constructing such resources and to the application of the method to a Russian lexicon, which results in the creation of the largest lexical resource of Russian derivational relations. The resulting database dubbed DeriNet.RU includes more than 300 thousand lexemes connected with more than 164 thousand binary derivational relations. To create such data, we combined the existing machine-learning methods that we improved to manage this goal. The whole approach is evaluated on our newly created data set of manual, parallel annotation. The resulting DeriNet.RU is freely available under an open license agreement.