Consider a continuous word embedding model. Usually, the cosines between word vectors are used as a measure of similarity of words. These cosines do not change under orthogonal transformations of the embedding space. We demonstrate that, using some canonical orthogonal transformations from SVD, it is possible both to increase the meaning of some components and to make the components more stable under re-learning. We study the interpretability of components for publicly available models for the Russian language (RusVectores, fastText, RDT).
The article provides lexical statistical analysis of K. Vonnegut's two novels and their Russian translations. It is found out that there happen some changes between the speed of word types and word tokens ratio change in the source and target texts. The author hypothesizes that these changes are typical for English-Russian translations, and moreover, they represent an example of Baker's translation feature of levelling out.
We present RuDSI, a new benchmark for word sense induction (WSI) in Russian. The dataset was created using manual annotation and semi-automatic clustering of Word Usage Graphs (WUGs). Unlike prior WSI datasets for Russian, RuDSI is completely data-driven (based on texts from Russian National Corpus), with no external word senses imposed on annotators. Depending on the parameters of graph clustering, different derivative datasets can be produced from raw annotation. We report the performance that several baseline WSI methods obtain on RuDSI and discuss possibilities for improving these scores.
The paper reports our participation in the shared task on word sense induction and disambiguation for the Russian language (RUSSE-2018). Our team was ranked 2nd for the wiki-wiki dataset (containing mostly homonyms) and 5th for the bts-rnc and active-dict datasets (containing mostly polysemous words) among all 19 participants. The method we employed was extremely naive. It implied representing contexts of ambiguous words as averaged word embedding vectors, using off-the-shelf pre-trained distributional models. Then, these vector representations were clustered with mainstream clustering techniq…
National Research University Higher School of Economics（国家研究型高等经济学院）
In this study we address the problem of automated word stress detection in Russian using character level models and no part-speech-taggers. We use a simple bidirectional RNN with LSTM nodes and achieve the accuracy of 90% or higher. We experiment with two training datasets and show that using the data from an annotated corpus is much more efficient than using a dictionary, since it allows us to take into account word frequencies and the morphological context of the word.
We present a deterministic algorithm for Russian inflection. This algorithm is implemented in a publicly available web-service www.passare.ru which provides functions for inflection of single words, word matching and synthesis of grammatically correct Russian text. The inflectional functions have been tested against the annotated corpus of Russian language OpenCorpora.
The most studied and most successful language models were developed and evaluated mainly for English and other close European languages, such as French, German, etc. It is important to study applicability of these models to other languages. The use of vector space models for Russian was recently studied for multiple corpora, such as Wikipedia, RuWac, lib.ru. These models were evaluated against word semantic similarity task. For our knowledge Twitter was not considered as a corpus for this task, with this work we fill the gap. Results for vectors trained on Twitter corpus are comparable in accu…
National Research University Higher School of Economics（国立研究型大学高等经济学院）；University of Oslo（奥斯陆大学）
The paper introduces manually annotated test sets for the task of tracing diachronic (temporal) semantic shifts in Russian. The two test sets are complementary in that the first one covers comparatively strong semantic changes occurring to nouns and adjectives from pre-Soviet to Soviet times, while the second one covers comparatively subtle socially and culturally determined shifts occurring in years from 2000 to 2014. Additionally, the second test set offers more granular classification of shifts degree, but is limited to only adjectives. The introduction of the test sets allowed us to evalua…
University of Oslo（奥斯陆大学）；University of Tyumen（秋明大学）
In this paper, we present a distributional word embedding model trained on one of the largest available Russian corpora: Araneum Russicum Maximum (over 10 billion words crawled from the web). We compare this model to the model trained on the Russian National Corpus (RNC). The two corpora are much different in their size and compilation procedures. We test these differences by evaluating the trained models against the Russian part of the Multilingual SimLex999 semantic similarity dataset. We detect and describe numerous issues in this dataset and publish a new corrected version. Aside from the …
Chatme AI LLC（Chatme AI 有限责任公司）；Novosibirsk State University（新西伯利亚国立大学）
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 supervised classifier with a composed word embeddings of two posts. Considering that the success in this task could be quite sensitive to the choice of word representations, we propose a comparison of the performance of different word embedding mo…
University of Hamburg（汉堡大学）；National Research University Higher School of Economics（国立研究型大学高等经济学院）；The Vinogradov Institute of the Russian Language, Russian Academy of Sciences（俄罗斯科学院维诺格拉多夫俄语研究所）；University of Mannheim（曼海姆大学）；Krasovskii Institute of Mathematics and Mechanics（克拉索夫斯基数学与力学研究所）；Scrapinghub（Scrapinghub公司）；Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）；Samsung Moscow Research Center（三星莫斯科研究中心）；ABBYY（ABBYY公司）
The paper describes the results of the first shared task on word sense induction (WSI) for the Russian language. While similar shared tasks were conducted in the past for some Romance and Germanic languages, we explore the performance of sense induction and disambiguation methods for a Slavic language that shares many features with other Slavic languages, such as rich morphology and virtually free word order. The participants were asked to group contexts of a given word in accordance with its senses that were not provided beforehand. For instance, given a word "bank" and a set of contexts for …
This paper evaluates morphology-based embeddings for English and Russian languages. Despite the interest and introduction of several morphology-based word embedding models in the past and acclaimed performance improvements on word similarity and language modeling tasks, in our experiments, we did not observe any stable preference over two of our baseline models - SkipGram and FastText. The performance exhibited by morphological embeddings is the average of the two baselines mentioned above.
University of Oslo（奥斯陆大学）；University of Helsinki（赫尔辛基大学）；National Research University Higher School of Economics（国立研究型大学高等经济学院）
We present our experience in applying distributional semantics (neural word embeddings) to the problem of representing and clustering documents in a bilingual comparable corpus. Our data is a collection of Russian and Ukrainian academic texts, for which topics are their academic fields. In order to build language-independent semantic representations of these documents, we train neural distributional models on monolingual corpora and learn the optimal linear transformation of vectors from one language to another. The resulting vectors are then used to produce `semantic fingerprints' of document…
We study the variation of word frequencies in Russian literary texts. Our findings indicate that the standard deviation of a word's frequency across texts depends on its average frequency according to a power law with exponent $0.62,$ showing that the rarer words have a relatively larger degree of frequency volatility (i.e., "burstiness"). Several latent factors models have been estimated to investigate the structure of the word frequency distribution. The dependence of a word's frequency volatility on its average frequency can be explained by the asymmetry in the distribution of latent factor…
ITMO University（圣彼得堡国立信息技术、机械学与光学研究型大学）；Faculty of Software Engineering and Computer Systems（软件工程与计算机系统学院）
In this paper, we present Russian language datasets in the digital humanities domain for the evaluation of word embedding techniques or similar language modeling and feature learning algorithms. The datasets are split into two task types, word intrusion and word analogy, and contain 31362 task units in total. The characteristics of the tasks and datasets are that they build upon small, domain-specific corpora, and that the datasets contain a high number of named entities. The datasets were created manually for two fantasy novel book series ("A Song of Ice and Fire" and "Harry Potter"). We prov…
Toxicity has become a grave problem for many online communities and has been growing across many languages, including Russian. Hate speech creates an environment of intimidation, discrimination, and may even incite some real-world violence. Both researchers and social platforms have been focused on developing models to detect toxicity in online communication for a while now. A common problem of these models is the presence of bias towards some words (e.g. woman, black, jew) that are not toxic, but serve as triggers for the classifier due to model caveats. In this paper, we describe our efforts…
A number of morphology-based word embedding models were introduced in recent years. However, their evaluation was mostly limited to English, which is known to be a morphologically simple language. In this paper, we explore whether and to what extent incorporating morphology into word embeddings improves performance on downstream NLP tasks, in the case of morphologically rich Russian language. NLP tasks of our choice are POS tagging, Chunking, and NER -- for Russian language, all can be mostly solved using only morphology without understanding the semantics of words. Our experiments show that m…
Abbreviation is a method of word formation that aims to construct the shortened term from the first letters of the initial phrase. Implicit abbreviations frequently cause the comprehension difficulties for unprepared readers. In this paper, we propose an efficient ML-based algorithm which allows to identify the abbreviations in Russian texts. The method achieves ROC AUC score 0.926 and F1 score 0.706 which are confirmed as competitive in comparison with the baselines. Along with the pipeline, we also establish first to our knowledge Russian dataset that is relevant for the desired task.
In this paper, we present a study of neologisms and loan words frequently occurring in Facebook user posts. We have analyzed a dataset of several million publically available posts written during 2006-2013 by Russian-speaking Facebook users. From these, we have built a vocabulary of most frequent lemmatized words missing from the OpenCorpora dictionary the assumption being that many such words have entered common use only recently. This assumption is certainly not true for all the words extracted in this way; for that reason, we manually filtered the automatically obtained list in order to exc…
University of Oslo（奥斯陆大学）；University of Trento（特伦托大学）
We critically evaluate the widespread assumption that deep learning NLP models do not require lemmatized input. To test this, we trained versions of contextualised word embedding ELMo models on raw tokenized corpora and on the corpora with word tokens replaced by their lemmas. Then, these models were evaluated on the word sense disambiguation task. This was done for the English and Russian languages. The experiments showed that while lemmatization is indeed not necessary for English, the situation is different for Russian. It seems that for rich-morphology languages, using lemmatized training …
pymorphy2 is a morphological analyzer and generator for Russian and Ukrainian languages. It uses large efficiently encoded lexi- cons built from OpenCorpora and LanguageTool data. A set of linguistically motivated rules is developed to enable morphological analysis and generation of out-of-vocabulary words observed in real-world documents. For Russian pymorphy2 provides state-of-the-arts morphological analysis quality. The analyzer is implemented in Python programming language with optional C++ extensions. Emphasis is put on ease of use, documentation and extensibility. The package is distribu…
National Research University Higher School of Economics（俄罗斯国立高等经济研究大学）；University of Oslo（奥斯陆大学）
We study the effectiveness of contextualized embeddings for the task of diachronic semantic change detection for Russian language data. Evaluation test sets consist of Russian nouns and adjectives annotated based on their occurrences in texts created in pre-Soviet, Soviet and post-Soviet time periods. ELMo and BERT architectures are compared on the task of ranking Russian words according to the degree of their semantic change over time. We use several methods for aggregation of contextualized embeddings from these architectures and evaluate their performance. Finally, we compare unsupervised a…
TU Darmstadt（达姆施塔特工业大学）；Ural Federal University（乌拉尔联邦大学）；Moscow State University（莫斯科国立大学）；University of Trento（特伦托大学）；University of Wolverhampton（沃尔夫汉普顿大学）
Semantic relatedness of terms represents similarity of meaning by a numerical score. On the one hand, humans easily make judgments about semantic relatedness. On the other hand, this kind of information is useful in language processing systems. While semantic relatedness has been extensively studied for English using numerous language resources, such as associative norms, human judgments, and datasets generated from lexical databases, no evaluation resources of this kind have been available for Russian to date. Our contribution addresses this problem. We present five language resources of diff…
The National Research University Higher School of Economics（国立研究型大学高等经济学院）；Federal Research Center `Computer Science and Control' of Russian Academy of Sciences（俄罗斯科学院计算机科学与控制联邦研究中心）
In recent years a certain success in the task of modeling lexical semantics was obtained with distributional semantic models. Nevertheless, the scientific community is still unaware what is the most reliable evaluation method for these models. Some researchers argue that the only possible gold standard could be obtained from neuro-cognitive resources that store information about human cognition. One of such resources is eye movement data on silent reading. The goal of this work is to test the hypothesis of whether such data could be used to evaluate distributional semantic models on different …
Moscow Institute of Physics and Technology（莫斯科物理技术学院）；Vietnam Maritime University（越南海事大学）
Named Entity Recognition (NER) is one of the most common tasks of the natural language processing. The purpose of NER is to find and classify tokens in text documents into predefined categories called tags, such as person names, quantity expressions, percentage expressions, names of locations, organizations, as well as expression of time, currency and others. Although there is a number of approaches have been proposed for this task in Russian language, it still has a substantial potential for the better solutions. In this work, we studied several deep neural network models starting from vanill…
Skolkovo Institute of Science and Technology (Skoltech)（斯科尔科沃科学技术学院（Skoltech））；Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）
This paper describes the results of the first shared task on taxonomy enrichment for the Russian language. The participants were asked to extend an existing taxonomy with previously unseen words: for each new word their systems should provide a ranked list of possible (candidate) hypernyms. In comparison to the previous tasks for other languages, our competition has a more realistic task setting: new words were provided without definitions. Instead, we provided a textual corpus where these new terms occurred. For this evaluation campaign, we developed a new evaluation dataset based on unpublis…
Samsung R&D Institute Russia（三星俄罗斯研发研究院）；Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）；SlickJump（SlickJump公司）
Word sense induction (WSI) is the problem of grouping occurrences of an ambiguous word according to the expressed sense of this word. Recently a new approach to this task was proposed, which generates possible substitutes for the ambiguous word in a particular context using neural language models, and then clusters sparse bag-of-words vectors built from these substitutes. In this work, we apply this approach to the Russian language and improve it in two ways. First, we propose methods of combining left and right contexts, resulting in better substitutes generated. Second, instead of fixed numb…
ASELSAN Research Center（阿瑟兰研究中心）；Bilkent University（比尔肯特大学）；Ludwig Maximillian University（路德维希·马克西米利安大学）
As an ubiquitous method in natural language processing, word embeddings are extensively employed to map semantic properties of words into a dense vector representation. They capture semantic and syntactic relations among words but the vectors corresponding to the words are only meaningful relative to each other. Neither the vector nor its dimensions have any absolute, interpretable meaning. We introduce an additive modification to the objective function of the embedding learning algorithm that encourages the embedding vectors of words that are semantically related to a predefined concept to ta…
National Research University Higher School of Economics（俄罗斯国家研究型高等经济大学）；Mail.ru Group（Mail.ru集团）
Distributed vector representations for natural language vocabulary get a lot of attention in contemporary computational linguistics. This paper summarizes the experience of applying neural network language models to the task of calculating semantic similarity for Russian. The experiments were performed in the course of Russian Semantic Similarity Evaluation track, where our models took from the 2nd to the 5th position, depending on the task. We introduce the tools and corpora used, comment on the nature of the shared task and describe the achieved results. It was found out that Continuous Skip…
TU Darmstadt（达姆施塔特工业大学）；Université catholique de Louvain（鲁汶天主教大学）；Moscow State University（莫斯科国立大学）；N. N. Krasovskii Institute of Mathematics and Mechanics, Ural Branch of the RAS（俄罗斯科学院乌拉尔分院N. N. 克拉索夫斯基数学与力学研究所）；NLPub；University of Trento（特伦托大学）；University of Wolverhampton（伍尔弗汉普顿大学）
The paper gives an overview of the Russian Semantic Similarity Evaluation (RUSSE) shared task held in conjunction with the Dialogue 2015 conference. There exist a lot of comparative studies on semantic similarity, yet no analysis of such measures was ever performed for the Russian language. Exploring this problem for the Russian language is even more interesting, because this language has features, such as rich morphology and free word order, which make it significantly different from English, German, and other well-studied languages. We attempt to bridge this gap by proposing a shared task on…
Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）；Samsung Moscow Research Center（三星莫斯科研究中心）；University of Hamburg（汉堡大学）
The paper describes our participation in the first shared task on word sense induction and disambiguation for the Russian language RUSSE'2018 (Panchenko et al., 2018). For each of several dozens of ambiguous words, the participants were asked to group text fragments containing it according to the senses of this word, which were not provided beforehand, therefore the "induction" part of the task. For instance, a word "bank" and a set of text fragments (also known as "contexts") in which this word occurs, e.g. "bank is a financial institution that accepts deposits" and "river bank is a slope bes…
Mail.ru Group（Mail.ru集团）；National Research University Higher School of Economics（国立研究型高等经济学院）
The paper deals with word sense induction from lexical co-occurrence graphs. We construct such graphs on large Russian corpora and then apply this data to cluster Mail.ru Search results according to meanings of the query. We compare different methods of performing such clustering and different source corpora. Models of applying distributional semantics to big linguistic data are described.
Unsupervised representation learning of words from large multilingual corpora is useful for downstream tasks such as word sense disambiguation, semantic text similarity, and information retrieval. The representation precision of log-bilinear fastText models is mostly due to their use of subword information. In previous work, the optimization of fastText's subword sizes has not been fully explored, and non-English fastText models were trained using subword sizes optimized for English and German word analogy tasks. In our work, we find the optimal subword sizes on the English, German, Czech, Ita…
ASELSAN Research Center（ASELSAN研究中心）；Bilkent University（比尔肯大学）
Dense word embeddings, which encode semantic meanings of words to low dimensional vector spaces have become very popular in natural language processing (NLP) research due to their state-of-the-art performances in many NLP tasks. Word embeddings are substantially successful in capturing semantic relations among words, so a meaningful semantic structure must be present in the respective vector spaces. However, in many cases, this semantic structure is broadly and heterogeneously distributed across the embedding dimensions, which makes interpretation a big challenge. In this study, we propose a s…
Word embeddings are substantially successful in capturing semantic relations among words. However, these lexical semantics are difficult to be interpreted. Definition modeling provides a more intuitive way to evaluate embeddings by utilizing them to generate natural language definitions of corresponding words. This task is of great significance for practical application and in-depth understanding of word representations. We propose a novel framework for definition modeling, which can generate reasonable and understandable context-dependent definitions. Moreover, we introduce usage modeling and…
Recent NLP literature has seen growing interest in improving model interpretability. Along this direction, we propose a trainable neural network layer that learns a global interaction graph between words and then selects more informative words using the learned word interactions. Our layer, we call WIGRAPH, can plug into any neural network-based NLP text classifiers right after its word embedding layer. Across multiple SOTA NLP models and various NLP datasets, we demonstrate that adding the WIGRAPH layer substantially improves NLP models' interpretability and enhances models' prediction perfor…
RWTH Aachen（亚琛工业大学）；L3S Research Center（L3S研究中心）；University of Mannheim（曼海姆大学）；GESIS（盖泽斯社会科学研究所）；CSH Vienna（维也纳复杂科学中心）
Adding interpretability to word embeddings represents an area of active research in text representation. Recent work has explored thepotential of embedding words via so-called polar dimensions (e.g. good vs. bad, correct vs. wrong). Examples of such recent approaches include SemAxis, POLAR, FrameAxis, and BiImp. Although these approaches provide interpretable dimensions for words, they have not been designed to deal with polysemy, i.e. they can not easily distinguish between different senses of words. To address this limitation, we present SensePOLAR, an extension of the original POLAR framewo…
Large pre-trained language models are capable of generating varied and fluent texts. Starting from the prompt, these models generate a narrative that can develop unpredictably. The existing methods of controllable text generation, which guide the narrative in the text in the user-specified direction, require creating a training corpus and an additional time-consuming training procedure. The paper proposes and investigates Collocation2Text, a plug-and-play method for automatic controllable text generation in Russian, which does not require fine-tuning. The method is based on two interacting mod…
In this paper we show that if we want to obtain human evidence about conventionalization of some phrases, we should ask native speakers about associations they have to a given phrase and its component words. We have shown that if component words of a phrase have each other as frequent associations, then this phrase can be considered as conventionalized. Another type of conventionalized phrases can be revealed using two factors: low entropy of phrase associations and low intersection of component word and phrase associations. The association experiments were performed for the Russian language.
To build an interpretable neural text classifier, most of the prior work has focused on designing inherently interpretable models or finding faithful explanations. A new line of work on improving model interpretability has just started, and many existing methods require either prior information or human annotations as additional inputs in training. To address this limitation, we propose the variational word mask (VMASK) method to automatically learn task-specific important words and reduce irrelevant information on classification, which ultimately improves the interpretability of model predict…
University of Ljubljana（卢布尔雅那大学）；University of Helsinki（赫尔辛基大学）；University of Tartu（塔尔图大学）；University of Latvia（拉脱维亚大学）
In text processing, deep neural networks mostly use word embeddings as an input. Embeddings have to ensure that relations between words are reflected through distances in a high-dimensional numeric space. To compare the quality of different text embeddings, typically, we use benchmark datasets. We present a collection of such datasets for the word analogy task in nine languages: Croatian, English, Estonian, Finnish, Latvian, Lithuanian, Russian, Slovenian, and Swedish. We redesigned the original monolingual analogy task to be much more culturally independent and also constructed cross-lingual …
On the Interpretability and Significance of Bias Metrics in Texts: a PMI-based Approach
Instituto de Investigación en Ciencias de la Computación, CONICET-UBA（CONICET-布宜诺斯艾利斯大学计算机科学研究所）；Universidad de Buenos Aires（布宜诺斯艾利斯大学）；CONICET（阿根廷国家科学与技术研究理事会）；Universidad Nacional de San Martín（圣马丁国立大学）；Harvard University（哈佛大学）
Grammatical cues to subjecthood are redundant in a majority of simple clauses across languages
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Vanderbilt University（范德堡大学）；Massachusetts Institute of Technology（麻省理工学院）；University of California, Irvine（加州大学欧文分校）
University of Mannheim（曼海姆大学）；Ural Federal University（乌拉尔联邦大学）
In this paper, we present Watasense, an unsupervised system for word sense disambiguation. Given a sentence, the system chooses the most relevant sense of each input word with respect to the semantic similarity between the given sentence and the synset constituting the sense of the target word. Watasense has two modes of operation. The sparse mode uses the traditional vector space model to estimate the most similar word sense corresponding to its context. The dense mode, instead, uses synset embeddings to cope with the sparsity problem. We describe the architecture of the present system and al…
Isfahan University of Technology（伊斯法罕理工大学）；Isfahan University of Medical Sciences（伊斯法罕医科大学）
Word embeddings have found their way into a wide range of natural language processing tasks including those in the biomedical domain. While these vector representations successfully capture semantic and syntactic word relations, hidden patterns and trends in the data, they fail to offer interpretability. Interpretability is a key means to justification which is an integral part when it comes to biomedical applications. We present an inclusive study on interpretability of word embeddings in the medical domain, focusing on the role of sparse methods. Qualitative and quantitative measurements and…
This work presents an unsupervised approach for improving WordNet that builds upon recent advances in document and sense representation via distributional semantics. We apply our methods to construct Wordnets in French and Russian, languages which both lack good manual constructions.1 These are evaluated on two new 600-word test sets for word-to-synset matching and found to improve greatly upon synset recall, outperforming the best automated Wordnets in F-score. Our methods require very few linguistic resources, thus being applicable for Wordnet construction in low-resources languages, and may…
National Research University Higher School of Economics（国立研究型大学高等经济学院）；Federal Research Center ‘Computer Science and Control’ of the Russian Academy of Sciences（俄罗斯科学院计算机科学与控制联邦研究中心）；Skolkovo Institute of Science and Technology (Skoltech)（斯科尔科沃科学技术研究所（斯科尔泰克））
The aim of this work is to explore the possible limitations of existing methods of cross-language word embeddings evaluation, addressing the lack of correlation between intrinsic and extrinsic cross-language evaluation methods. To prove this hypothesis, we construct English-Russian datasets for extrinsic and intrinsic evaluation tasks and compare performances of 5 different cross-language models on them. The results say that the scores even on different intrinsic benchmarks do not correlate to each other. We can conclude that the use of human references as ground truth for cross-language word …
