=Paper=
{{Paper
|id=Vol-2552/Paper22
|storemode=property
|title=Russian Prepositional Phrase Semantic Labelling with Word Embedding-based Classifier
|pdfUrl=https://ceur-ws.org/Vol-2552/Paper22.pdf
|volume=Vol-2552
|authors=Vadim Gudkov,Anastasia Golovina,Olga Mitrofanova,Victor Zakharov
}}
==Russian Prepositional Phrase Semantic Labelling with Word Embedding-based Classifier
==
https://ceur-ws.org/Vol-2552/Paper22.pdf
Russian Prepositional Phrase Semantic Labelling
with Word Embedding-based Classifier ∗
Vadim Gudkov1 Anastasia Golovina 1
vadim0006@gmail.com besiage@gmail.com
Olga Mitrofanova 1 Victor Zakharov 1
o.mitrofanova@spbu.ru v.zakharov@spbu.ru
1
Saint Petersburg State University,
Saint Petersburg Russian Federation
Abstract
This paper discusses experiments on automatic extraction, classification and semantic
labelling of prepositional phrases in a Russian text corpus. Semantic description of prepo-
sitional phrases used in our study is based on G.A. Zolotova’s simplified classification of
minimal language entities. We present the experimental setup, explain the procedure of
the training dataset development, describe the labelling techniques, and provide analysis
of results. Our research shows that although semantic differences between some preposi-
tional semantic classes are quite vague, it is possible to achieve promising classification
results for core classes.
Keywords: prepositional phrases, short text classification, word embeddings, seman-
tic labelling.
1 Introduction
Semantic labelling is understood as the task of annotating language units with labels de-
noting their semantic meaning or role. Although the most common variation of this task is
Semantic Role Labelling, the process of attaching labels carrying semantic role information
of the predicate-argument structure to sentence parts, that is not the only way of classifying
semantic categories. The experiment described in this paper deals with a wider interpretation
of semantic labelling - that is, the process of assigning semantic category labels to syntactic
constructions, namely prepositional phrases.
Although there exist multiple theoretical classifications of prepositional phrases in litera-
ture with respect to their semantics, and there is strong evidence which suggests that semantic
information is highly useful for tasks which traditionally rely on structural features (such as
∗
Copyright c 2019 for this paper by its authors. Use permitted under Creative Commons License Attri-
bution 4.0 International (CC BY 4.0).
1
parsing), the topic of semantic disambiguation of prepositional phrases is underdeveloped.
The study presented in this paper is an attempt to explore this problem.
The preliminary research on the topic of semantic labelling applied to prepositional
phrases showed that no classification suitable for NLP tasks had been developed or adapted
for the Russian language. Additionally, no corpus big and representative enough specifically
for studying prepositional phrases had been available. Therefore, we took the matter into our
own hands and created the first corpus of this kind for Russian prepositional phrases. The
phrases in our corpus consist of three elements: the head, the preposition and the dependent
noun phrase. A more detailed description is offered in Section 3.2.
Having dealt with the corpus issue, we approached the next stage of our task: the selection
of the semantic classification to be used for annotating the acquired prepositional phrases.
However, the existing semantic interpretations of prepositions and their relations proved to be
unfit for use in our study due to their high degree of granularity and the lack of consistency.
We ended up adapting one of them to suit the needs dictated by our task. The classification
described in this paper is heavily based on the work of our predecessors, however, ours differs
in that it was created specifically with the NLP applicability in mind.
In the early stages of our study we took notice of another problem that has to do with
the core element of a prepositional phrase - the preposition. Although an indisputable part
of the Russian lexicon and morphological system, prepositions remain a class with blurred
boundaries. Russian prepositions are commonly divided into non-derivative, simple derivative
and complex derivative [Shvedova, 1980]. While the non-derivative prepositions are a closed
class, the list of their derivative counterparts remains disputed and varies greatly from source
to source, some being considered to be improper prepositions. It is therefore not surprising
that although the core, non-derivative prepositions have enjoyed attention in literature, the
derivative prepositions are still understudied, especially in computational linguistics.
While generating the prepositional phrase corpus used in this study we paid special at-
tention to derivative prepositions and functional phrases containing prepositions. We went
beyond the more commonly observed practice of treating only prepositional phrases with
simple prepositions as valid and included complex derivative prepositions into our subject of
study as well. We also took heed of functional set phrases containing prepositions as to avoid
treating them as part of a prepositional phrase.
The main objective of our experiment was to study the potential of distributed word rep-
resentations in a vector space model in semantic description of Russian prepositional phrases.
In order to do that, we set out to perform a classification of prepositional semantic categories
using a supervised machine learning algorithm trained on a corpus of manually tagged preposi-
tional phrases. The primary hypothesis of our study was that word embeddings of prepositional
constructions can include representations of semantic categories intrinsic to prepositions. This
study was conducted as part of the RFBR project 17-29-09159 “Quantitative grammar of Rus-
sian prepositional constructions” carried out at the Department of Mathematical Linguistics,
Saint Petersburg State University, Russia [Zakharov, 2017; Zakharov and Azarova, 2019]. The
comprehensive goal of the project is to create a representative quantitative lexical-grammatic
description of Russian prepositions based on corpus data, with a strong focus on the semantic
features of prepositional constructions, as this is something that has not been comprehensively
studied as of yet.
The rest of the paper is structured as follows. Section 2 provides theoretical groundings
of the prepositional phrase semantic classification applied in our project. In Section 3 we
describe our approach and the technical details of our experiment. Section 4 is dedicated to
2
data analysis as well as to the discussion of tendencies revealed by the output errors. Finally,
Section 5 concludes and outlines some directions for future research.
2 Related Work
Traditional linguistic methods are based on the understanding of language as a multilevel
system, each linguistic level having its own elementary unit. Modern research practices, how-
ever, lean towards an integral view focused on language structures uniting different linguistic
elementary units. This view has been developed within Construction grammar (Ch. Fillmore
and his followers: [Fillmore, 1988], see also an overview of the trend in [Rakhilina, 2010]).
Within this theory, constructions are regarded as complex signs comprising units of various
linguistic levels which constitute a functional whole and not a mere sum of their elements.
The given approach was adopted in our study. Namely, we assume that the meaning of a
preposition defines the semantic features of the whole prepositional phrase, and vice versa,
the semantic and syntactic connection between words in a prepositional phrase is understood
as a realization of a particular prepositional meaning.
Most of the studies concerned with prepositional phrases have been related to the preposi-
tional phrase attachment disambiguation task as it remains one of the main sources of parsing
errors. It has been proven that the use of distributed word representations may improve
prepositional phrase attachment accuracy [Agirre et al., 2008; Belinkov et al., 2014; Dasigi et
al., 2017]. Therefore, we hypothesize that a similar approach may be helpful in our case as
well.
A study akin to ours has been performed and discussed in [Rudzizc and Mokhov, 2010],
although the number of classes selected was considerably lower (only 7 classes were chosen).
It must be noted that there exists no commonly accepted semantic classification of Russian
prepositional phrases as of yet. As the performance of our system would crucially depend on
the semantic classification used, it was necessary to either adapt an existing one to fit the
needs of our task or develop our own.
The most obvious approach which implies extraction of prepositional meanings from a
dictionary proved to be unfit for the task on hand. Although most dictionaries do offer defini-
tions for functional parts of speech such as prepositions, the word senses they distinguish are
not suitable for use in NLP tasks. As such, the three dictionaries we studied, Small Academic
Dictionary of the Russian Language, Wiktionary, Explanatory Dictionary of the Russian lan-
guage by S.I. Ozhegov and N.Ju. Shvedova, had the same critical problems. Firstly, the format
of the definitions themselves (their number, volume, content and granularity) fully depend on
the format of the dictionary itself. We found the senses used in the diction-aries examined
for our task to be too fine-grained, often including rare, orthodox and metaphorical senses.
Another problem lay in the lack of any systematic approach to defining the prepositional
senses: a preposition is defined with no regard for another preposition’s senses, making the
creation of a uniform classification entirely impossible. Additionally, no syn-tactic features of
prepositional phrases other than the dependent’s case were included in the definitions, making
the dictionary senses of prepositions harder to study from the point of view of syntactic units.
A much more appropriate approach was discovered in the Syntactic Dictionary by G.A.
Zolotova [Zolotova, 1988]. In this work, G.A. Zolotova introduces the minimal syntactic unit
called syntaxeme in order to describe the syntactic structure of the Russian language. A big
part of the dictionary is dedicated to prepositional syntaxemes understood as the combination
3
of a preposition and the case of its nominal dependent, for instance, the preposition ‘в’ plus the
accusative case. G.A. Zolotova describes the functional dependency relations of a syntaxeme as
well as its semantic meanings, which makes the Syntactic Dictionary a better-suited resource
for the purposes of studying semantic features of syntactic constructions. G.A. Zolotova also
offers a systematically disjointed yet highly detailed sense classification of syntaxemes, defining
such sense types as Location, Direction, Instrument etc., subdivided further in accordance with
their dependency relations. Although this classification is also highly fine-grained, we felt it
could be successfully adapted for use in our modelling task. Another shortcoming of G.A.
Zolotova’s dictionary is the absence of most derivative prepositions, something we also at-
tempted to tackle in our study. An attempt at adapting G.A. Zolotova’s classification for use
in NLP tasks can be found in [Mikhailova, 2015]. V.D. Mikhailova revised G.A. Zolotova’s
classes, uniting minor senses into bigger ones and giving labels to the senses left un-named in
the original classification. However, the reworked classification (further referred to as Zolotova-
Mikhailova’s classification) still focused on the semantic features of separate prepositions as
opposed to the entire class and proved to be too complex for effective classification.
3 Our Approach
3.1 Generalization of Zolotova-Mikhailova’s classification
In order to reduce the drawbacks of the existing semantic classifications of prepositional senses,
we reworked the classes described in Zolotova-Mikhailova’s classification and proposed a single-
layer universal classification. To do that, we united the sense subcategories into larger classes
while also separating those with double sense labels into distinct classes. We clustered the
remaining classes by closeness of sense and united each of them into superclasses, ending up
with 15 classes in total.
3.2 Generating a Corpus
In order to prove the hypothesis, we developed a large and representative corpus of Russian
prepositional phrases, which at present has no analogues. We used a SynTagRus pretrained
UDPipe model [Straka and Straková, 2017] in order to extract the prepositions with the head
word and its dependant full noun phrases. The link to the tool developed for the task can be
found in the Appendix. The extraction pipeline is displayed in Figure 1.
We used a large dictionary of Russian simple and complex prepositions to verify the
parser’s decisions. The preposition list was compiled from dictionaries (Efremova, Sharoff,
Rogozhnikova, Small Academic Dictionary, Wiktionary) and corpora (RNC, OpenCorpora,
HANCO). Some normalization work was done in order to ensure that all variants of the same
preposition would be counted as one, as some prepositions come from the same root and are
only different in their form due to their being proclitics, such as ‘о/об/обо’, ‘без/безо’, ‘с/со’
etc. Such variants were therefore concatenated.
Simple and complex prepositions were treated in the same way. Complex prepositions
were interpreted as standalone units with their own attachments and dependants.
We also filtered out the prepositional homonyms as well as phrases with prepositions
which are parts of functional words and some idiomatic phrases. The list of such stop words
was extracted from the Explanatory dictionary of functional parts of speech of the Russian
language by T.F. Efremova [Efremova, 2004] and supplemented by the lists of set expressions
4
5
Figure 1: The full cycle of a PP extraction from raw text
containing prepositions provided by the Russian National Corpus. We also added OpenCor-
pora morphological annotation with the help of PyMorphy2 [Korobov, 2015] for the extracted
data in order to ease the subsequent annotation part.
Following this approach we parsed the Taiga news subcorpus [Shavrina, 2018] (size 92
million tokens) and acquired 5 million prepositional phrases. For each prepositional phrase
its head, preposition and dependant, alongside with their POS, lemmas and the case of the
dependant, were extracted as well. The absolute frequency distribution of the most commonly
occurring prepositions observed in the corpus is shown in Figure 2.
6
Figure 2: The distribution of 30 most common simple and complex prepositions in the corpus
3.3 Human Annotation
The generalization of Zolotova-Mikhailova’s classification furnished us with the final set of
semantic categories characterising prepositional phrases. The classification was manually ap-
plied to all of the prepositions described by G.A. Zolotova (mainly non-derivatives), yielding
the base set of semantically classified prepositional syntaxemes.
A randomly selected data subset of 10 000 phrases was then acquired from the original 5
7
million corpus for manual an-notation. The previously undescribed prepositional syntaxemes
observed in the subset were collected and classified as well.
Figure 3: Distribution of semantic classes in the manually labelled subcorpus
After that we created a form containing the list of the syntaxemes, all of the semantic
functions of each syntaxeme illustrated with definitions and examples, and tables containing
sets of untagged prepositional phrases from the subset sorted by syntaxeme. Thirty annotators
with linguistic background were then asked to perform sense disambiguation of prepositional
phrases based on the provided classification. After the disambiguation, all of the annotated
phrases were manually checked by experts. Figure 3 demonstrates the absolute frequency
distribution of the fifteen semantic categories used in our classification.
3.4 Classification Task
After acquiring the labelled dataset we were able to perform a supervised classification. The
preliminary analysis of the data uncovered the fact that the semantic classes are highly imbal-
anced in the corpus. The least represented of them are Instrument, Transgression, Situation
and Potential as opposed to Location, Theme and Tempus. This imbalance directly affected
the performance of the classifier, which leads us to the idea that class enhancement could be an
option for further research. However, this experiment is left out of the scope of this paper. In
our experiments we revised a standard strategy used in previous works on construction classifi-
cation [Lyashevskaya et al., 2013]. This strategy develops a view on constructions as multilevel
entities combining lexical, semantic, morphological and syntactic features. Context markers
constituting a set of constructions for a target word allow the identification of its meaning,
so that separate meanings of a polysemous word can be associated with independent clusters
of constructions. The procedures of word sense induction/disambiguation and semantic la-
8
belling thus can be fulfilled by means of super-vised construction classification [Lyashevskaya
et al., 2011]. Our approach is based on the assumption that classification of prepositional
phrases should be performed not for constructions per se but for their vector representations
obtained from Word2Vec models [Mikolov et al., 2013] trained on the Russian corpora from
the RusVectores project [Kutuzov et al., 2016]. In this respect, the vector of a prepositional
phrase is composed as a sum of vectors corresponding to lexical items constituting the whole
construction.
Our preprocessing procedure was performed in accordance with the technique proposed
in [Kutuzov and Kuzmenko, 2017], which comprised POS label attachment to the tokens. We
made multiple attempts with pretrained embeddings, alt-hough without achieving any viable
results with F1 score of 0.4 on average with traditional embedding approaches of TF-IDF and
Word2Vec.
We then decided to obtain our own word vectors via FastText supervised [Bojanowski et
al., 2016]. This tool enables word embedding via subword information, which has proven to be
extremely efficient for morphologically rich languages, such as Russian. Moreover, it utilizes
label information via a softmax layer to obtain a probability distribution over predefined
classes. With the help of this tool, the classification results were elevated to a higher level. As
regards F1 score, the categories Destination, Quantity, Location and Tempus are recognized
quite effectively, F1 measure being from 0.70 up to 0.86. The other categories achieve moderate
F1 values. Due to the highly unbalanced nature of the dataset, some of the lower represented
classes were not properly identified. However, average F1 score for the whole set of semantic
categories reaches 0.65 and may be boosted after certain improvement of the experimental
settings. Data on F1 measure values are given in Table 2.
4 Error Analysis
In order to uncover the tendencies in the classification errors we considered a random subset
of 300 prepositional constructions with manually assigned labels and those predicted by a
model. We found 95 mismatches between the given label and the predicted one, that roughly
corresponds to average F1 score evaluating the classification effectiveness. Thorough analysis
of the sample revealed true errors and meaningful mismatches.
However, a major factor influencing correctness of predicted labels was the disbalance
in the representation of semantic categories in the training data. As has been mentioned in
Section 3.4, several classes were significantly underrepresented in the training dataset. The
problem of data sparsity observed for those classes led to their predominance among the
mislabelled categories, among which we should mention Potential, Situation, Transgression
and Instrument as the least represented categories with the lowest F1 score.
We registered only a small number of true errors exemplified by short contexts with de-
ictic words (e.g. надо для этого, для этого остаться, etc.) and/or potentially ambiguous
parts (e.g. стать от такого региона, ставка по программе, etc.). Set expressions or
phraseological units (e.g. обратиться с просьбой) defy proper treatment for their possible
non-compositionality. In such cases it is hard to obtain the correct label prediction. Nonethe-
less, in most cases we found meaningful mismatches between labels assigned by experts and
those predicted by the model. The most common reason is the inevitable semantic fuzziness
of categories included in the generalized Zolotova-Mikhailova’s classification. We found sets of
prepositional phrases which should be treated as manifestations of merged semantic classes,
9
e.g. Object - Theme (e.g. заявлять о задержке зарплаты, сообщать о местонахождении
обвиняемого, ходатайствовать о рассмотрении дела, предупреждать о закрытии, etc.);
Tempus - Location (находиться в процессе предварительного расследования, видеть в
процессе этого занятия, etc.); Direction - Location (выстрел в воздух, доставить на
станцию Акуловка, etc.); Destination - Location (обращаться во все инстанции, etc.);
Source - Location (прописать в регламенте, отыскаться в решении арбитражного суда,
etc.); Cause - Quality (откликнуться на предложение, etc.), and so on. In the aforemen-
tioned cases the differences between the semantic categories are subtle, so that prepositional
phrases with dual labels seem to be immanently ambiguous as they possibly reveal both
categories simultaneously. Such prepositional phrases can obtain proper treatment as con-
structions with diffuse meaning according to Ju.D. Apresjan [Apresjan, 1971]. In such cases
differentiation of close meanings turns out to be impossible.
5 Conclusion аnd Future Work
In this paper we proposed a challenging solution to the problem of automatic semantic clas-
sification of prepositional phrases. Although some attempts into classifying the semantic
functions of prepositions had been made, none proved to be effective from the point of view
of their application in NLP tasks. We used G.A. Zolotova’s system of syntaxeme senses to
develop a semantic classification of prepositional phrases which could be used in our task. We
then tested the developed classification in manual prepositional phrase sense disambiguation
and used the obtained data for training a word embedding-based classifier. The results of
the subsequent automatic classification of prepositional phrases presented in this article show
that some of the specified classes, such as Location, Tempus, Quantity and Destination, can
be identified with a high degree of success. At the same time, a few classes underrepresented
in the training data and having broader definitions presented a problem to the classifier.
The results attained with our method suggest several possible directions for further de-
velopment. The problem of data sparsity that affected the predictions received for the smaller
classes might be resolved through WordNet-based class enhancement, as was mentioned in
Section 3.3. Alternatively, the issue could be overcome by means of reworking the classifica-
tion itself to assign the prepositional phrases currently found in the poorer-performing classes
to the others. In addition to the aforementioned lines of practical research, the proposed clas-
sification of prepositional syntaxemes could be used for describing the previously unexplored
derivative prepositions. All in all, being the first of its kind for Russian prepositional phrases,
our study offers substantial food for thought for further research and experiments.
6 Appendix
The tool used for prepositional phrase extraction and semantic classification, and the data are
available at https://github.com/merionum/pphrase.
Acknowledgements
Our research was supported by the RFBR grant 17-29-09159 “Quantitative grammar of Russian
prepositional construc-tions” (2018-2020).
10
Authors wish to express their sincere gratitude to A.Ts. Masevich, U.V. Butorova, E.G.
Filimonov, D.A. Alfimova, A.D. Ivanova, the students of the SPbU Mathematical Linguistics
Department and other participants for their valuable help in annotating the data.
References
[Shvedova, 1980] Shvedova N.Ju. (1980) Russian Grammar. Vol. 1. Moscow, Nauka: 1980. –
792 p. (in Rus.) = Russkaja grammatika. Tom 1. Moscow, Nauka: 1980. – 792 s.
[Zakharov, 2017] Zakharov, V.P. (2017). A construction grammar approach to Russian prepo-
sitions. SGEM 4th International Multidisciplinary Scientific Conference on Social Sciences
and Arts 20172367-5659, 2(3), pp. 279-286.
[Zakharov and Azarova, 2019] Zakharov, V.P., and Azarova, I.V. (2019). Towards a compu-
tational ontology of Russian prepositions. Trudy mezhdunarodnoj konferencii “Korpusnaja
lingvistika", pp. 155-165.
[Fillmore, 1988] Fillmore, C.J. (1988). The Mechanisms of “Construction Grammar”. Pro-
ceedings of the Fourteenth Annual Meeting of the Berkeley Linguistics Society (1988), pp.
35-55.
[Rakhilina., 2010] Rakhilina, E.V. (2010) Construction linguistics. Moscow, Azbukovnik
Publ.: 2010. – 584 p. (in Rus.) = Lingvistika konstrukcij. Moscow, Azbukovnik: 2010.
– 584 s.
[Agirre et al., 2008] Agirre, E., Baldwin, T., Martı́nez, D. (2008). Improving Parsing and PP
Attachment Performance with Sense Information. In Proc. of the 46th Annual Meeting of
the Association for Computational Linguistics, pp. 317–325.
[Belinkov et al., 2014] Belinkov, Y., Lei, T., Barzilay, R., Globerson, A. (2014) Exploring
Compositional Architectures and Word Vector Representations for Prepositional Phrase
Attachment. Transactions of the Association for Computational Linguistics, 2, pp. 561-572.
[Dasigi et al., 2017] Dasigi, P., Ammar, W., Dyer, C., Hovy, E. (2017) Ontology-Aware Token
Embeddings for Preposi-tional Phrase Attachment. In Proc. of the 55th Annual Meeting
of the Association for Computational Lin-guistics (Vol 1: Long Papers), pp. 2089–2098.
[Rudzizc and Mokhov, 2010] Rudzicz, F., and Mokhov, S. (2010) Towards a Heuristic Cate-
gorization of Prepositional Phrases in English with WordNet. Technical Report, Cornell
University, (2003), arxiv1.library.cornell.edu/abs/1002.1095- ?context=cs
[Zolotova, 1988] Zolotova G.A. (1988) Syntactic dictionary: Repertory of elementary units
of Russian Syntax. Moscow: Nauka, 1988. – 440 p. (in Rus.) = Sintaksicheskij slovar’:
repertuar elementarnykh jedinic russkogo jazyka. Moscow: Nauka, 1988. – 440 s.
[Mikhailova, 2015] Mikhailova, V.D. (2015) Ontology of Prepositions in the Russian language.
Saint Petersburg, SPbU: 2015. - 159 p. (in Rus.) = Ontologija predlogov v russkom jazyke.
Saint Petersburg, SPbU: 2015. - 159 s. [Straka and Straková, 2017] Milan S., and Straková,
J. Tokenizing, POS Tagging, Lemmatizing and Parsing UD 2.0 with UDPipe. In Proceed-
ings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal
Dependencies, Vancouver, Canada, August 2017.
11
[Efremova, 2004] Efremova T.F. Explanatory dictionary of functional parts of speech of the
Russian language. Moscow: Astrel, AST, 2004. - 815 p. (in Rus.) = Tolkovyj slovar’
sluzhebnykh chastej rechi. Moscow, Astrel: 2004. – 815 s.
[Korobov, 2015] Korobov M. (2015) Morphological Analyzer and Generator for Russian and
Ukrainian Languages // Analysis of Images, Social Networks and Texts, pp 320-332. [Shav-
rina, 2018] Shavrina, T.O. (2018) Differential Approach to Web-Corpus Construction. In
Proc. of the 2018 Annual International Conference “Dialog”. Moscow, 2018. 11 p.
[Lyashevskaya et al., 2013] Lyashevskaya O.N., Panicheva P.V., Mitrofanova O.A. (2013)
Data visualization for building the catalogue of Russian lexical constructions (based on
RNC). In: Computational Linguistics and Intellec-tual Technologies: Papers from the
Annual International Conference “Dialogue” (2013). Issue 12. Vol. 1 P. 465-478.
[Lyashevskaya et al., 2011] Lyashevskaya O., Mitrofanova O., Grachkova M., Romanov S.,
Shimorina A., and Shurygi-na A. (2011) Automatic Word Sense Disambiguation and Con-
struction Identification Based on Corpus Multilevel Annotation. In: Text, Speech and
Dialogue. Proceedings of the 14th International Conference TSD 2011, Pilsen, Czech Re-
public, September 1–5, 2011. Springer-Verlag, 2011.
[Mikolov et al., 2013] Mikolov et al. (2013) Distributed Representations of Words and Phrases
and their Compositionality. In: Proceedings of Neural Information Processing Systems. 26
p. [Kutuzov and Kuzmenko, 2017] Kutuzov A., and Kuzmenko E. (2017) WebVectors: A
Toolkit for Building Web Interfac-es for Vector Semantic Models. In: Ignatov D. et al. (eds)
Analysis of Images, Social Networks and Texts. AIST 2016. Communications in Computer
and Information Science, vol 661. Springer, Cham.
[Bojanowski et al., 2016] Bojanowski, P., Grave, E., Joulin, A., Mikolov, T. (2016) Enriching
Word Vectors with Subword Information. Transactions of the Association for Computa-
tional Linguistics.
[Apresjan, 1971] Apresjan Ju.D. (1971) On regular polysemy. In: Proceedings of the Academy
of Sciences of the USSR. Department of Literature and Language. Vol. XXX. Issue 6. -
М., 1971. - P. 509-523. (in Rus.) = O regulyarnoj mnogoznachnosti. Izvestija AN SSSR.
Vol. XXX. Vyp. 6. - M., 1971. - s. 509-523.
12