Synonym Sets Research Articles

ЛЕКСИКОГРАФИЯТА – ИСТОРИЯ, ТЕОРИЯ И ПРАКТИКА / LEXICOGRAPHY – HISTORY, THEORY AND PRACTICE

The papers featured in Issue 2/2021 of the Journal deal with major topics in the theory and practice of lexicography – both in a contemporary and historical perspective. The authors address problems of onomastic lexicography, neography, explanatory lexicography and the history of Bulgarian dictionary crafting. One of the papers sheds light on some aspects of the lexicographic practice in Poland. The issue is dedicated to one of the most eminent representatives of contemporary Bulgarian academic lexicography – Prof. DSc Maria Choroleeva – on the occasion of her forthcoming jubilee. Boris Parashkevov’s paper outlines a project for the creation of a dictionary of Bulgarian surnames. The concept of the dictionary envisages the organisation of family names in nests based on semantic equivalence (correspondence), associative reference and shared structural membership, thus making it possible to reveal the structural and semantic relations among the names under study. In addition, the dictionary entries document the derivational paradigm of the respective surnames, including short forms, diminutives and suffixal derivatives. Sia Kolkovska addresses some peculiarities in the lexicographic description of Bulgarian neologisms motivated by specific types of polysemy and synonymy. The author comments on the lexicographic description of the semantic structure of new polysemous loanwords and discusses the criteria for selecting a dominant synonym in synonym sets composed of neologisms. Diana Blagoeva and Sia Kolkovska’s paper also deals with issues in neography. The authors discuss the views on the categorial nature of neologisms of the type бизнесцентър/бизнес център (business centre) in Bulgarian and comment on the reasons for the emergence and establishment of this type of lexemes in the language, while considering the dynamics of their functioning. The paper motivates the necessity for the application of a special approach to the lexicographic description of this type of neologisms. Tsvetelina Georgieva comments on Nayden Gerov’s understanding of the so-called „равнознаменаменователни речи“ and highlights the contribution of the renowned lexicographer of the National Revival and the Post-liberation period to the representation of such names in an explanatory dictionary. The author maintains that these names should be considered not synonyms but heteroyms as they belong to different dialects. Nadezhda Kostova also takes a look at the history of Bulgarian lexicography in her discussion on the arrangement of dictionary entries in different types of dictionaries from the beginning of the 20th century. The author provides a comparative analysis of the peculiarities in the application of the alphabetical-nest arrangement in the lexicographic works under discussion. In his paper Petar Sotirov studies the application of the qualifier colloquially (potoczne) in Polish explanatory lexicography, taking as a point of departure the views on the notion of colloquialism in Polish linguistics. The author concludes that the dominant notion of colloquialism in Polish lexicography is the stylistic one and goes on to identify certain cases of inconsistencies and discrepancies in the use of the qualifier. Mihaela Kuzmova discusses the place of precedent phenomena (in par-ticular, the so-called “winged words”) in phraseology. The author proposes an analysis of several popular expressions of domestic precedent origin which have neither been described in lexicographic works, nor commented in the linguistic literature, and offers some observations on their phraseologisation and usualisation.

Idea plagiarism detection with recurrent neural networks and vector space model

PurposeNatural languages have a fundamental quality of suppleness that makes it possible to present a single idea in plenty of different ways. This feature is often exploited in the academic world, leading to the theft of work referred to as plagiarism. Many approaches have been put forward to detect such cases based on various text features and grammatical structures of languages. However, there is a huge scope of improvement for detecting intelligent plagiarism.Design/methodology/approachTo realize this, the paper introduces a hybrid model to detect intelligent plagiarism by breaking the entire process into three stages: (1) clustering, (2) vector formulation in each cluster based on semantic roles, normalization and similarity index calculation and (3) Summary generation using encoder-decoder. An effective weighing scheme has been introduced to select terms used to build vectors based on K-means, which is calculated on the synonym set for the said term. If the value calculated in the last stage lies above a predefined threshold, only then the next semantic argument is analyzed. When the similarity score for two documents is beyond the threshold, a short summary for plagiarized documents is created.FindingsExperimental results show that this method is able to detect connotation and concealment used in idea plagiarism besides detecting literal plagiarism.Originality/valueThe proposed model can help academics stay updated by providing summaries of relevant articles. It would eliminate the practice of plagiarism infesting the academic community at an unprecedented pace. The model will also accelerate the process of reviewing academic documents, aiding in the speedy publishing of research articles.

Question Expansion Technique On The Different Translations Of The Holy Quran By Using WordNet And Islamic Synonyms

The Holy Quran is the most significant religious text, which is followedby thebelievers of the Islamic religion. The translations of the Quran are the interpretation of its meaning in different languages, to assist those who are not familiar with the Arabic language.Most of the Quranic search systems that support theneeds of who are non-native speakers of the Arabic language of the contents of the Holy Quran are basedon keywords matching. Since there are several known English translations of the Holy Quran and each translation has its terminology based on the style of the translator. In addition to that, there are Islamic terms might be not used in the English language, such as "Hajj" or "Saum,"where these terms might vary from one translation to another. Therefore, these search systems do not support the needs of the user, and often there isno matching between the terms of user's questionandtheterms of the Quran.Consequently, this research has used the synonymsofWordNet to expand the user's question,and to cover all the possibilities of theterms that might be usedin the Quran translation, but there are many of Islamic terms are not available in the WordNet database. The WordNet has been enhanced with a set of Islamic synonyms that have been used in the well-known Islamic translations of the English language, which it was created by the researcher, to increase the likelihood of providing a sure matching between the question's words and the contents of the Quran translation. According to the results of this study, the evaluation of this research proved that the method of question expansion by using the both of the WordNet and the Islamic synonyms showed better accuracy and efficiency than the traditional keywords matching systems, or the system that uses only the WordNet synonyms in the question expansion method in terms of matching all user's questions words with documents and retrieve the correct answers to these questions.

СИНОНИМИЯ В ВЫМЫШЛЕННЫХ ЯЗЫКАХ (НА МАТЕРИАЛЕ НА’ВИ И ДОТРАКИЙСКОГО ЯЗЫКОВ)

The article focuses on the description of synonymic sets in two fictional languages - Dothraki and Na'vi. The objective of the research is to identify the key characteristics of synonymic sets in these artlangs. In two languages, binary and polynary synonymic sets are formed, including ideographic, stylistic and semantic-stylistic synonyms. The authors reveal that synonyms differ in such semantic components as time, degree and attendant circumstances. In the Dothraki language, larger synonymic sets are formed to describe significant phenomena in the world of fictional people groups; synonymic sets of the Na'vi language are characterized by synonyms with a greater variety of components in the structure of their lexical meanings.

LEXICAL-SEMANTIC SUBSYSTEM OF SENSORY VERBS IN THE MODERN ENGLISH VERB SYSTEM

The article focuses on the study of the lexical-semantic subsystem of sensory verbs in the Modern English verb system. The objectives of the study are to analyse sensory verbs’ semantic features, establish macro- and micro integral connections between them, and to determine their groups and synonymic sets by differential trait and denotative sema. Definitional, componential, comparative, proportional and quantitative analysis, English explanatory dictionaries and thesauri were used in the study. Sensory verbs of five lexical-semantic fields have approximately the same proportion of lexemes that form the core, main part and periphery of each corresponding lexical-semantic field, with a slightly larger number of verbs in the main part. Old English sensory verbs make up a third of the modern perception process subsystem, almost a half of the borrowed lexemes from French and Latin, a tenth of sensory verbs borrowed from the West Germanic group and a small percentage is formed by borrowings from other languages, unknown or imitative origin. The study analysed the share of sensory verbs according to the periods of English language development. Sensory verbs of the Middle English and New English periods make up more than a half of the sensory vocabulary of the modern perception process subsystem. It is established that sensory verbs are combined into groups and synonymic sets by seven differential traits. The results of the study of connections between sensory verbs show that they are not isolated in their lexical-semantic fields and in general in the sensory subsystem of the sensory perception process, i.e. they migrate between sensory lexical-semantic fields. All the lexemes of the sensory subsystem are hierarchical, belong to the hierarchy of lexical-semantic formations and implicitly have all the features of the higher levels of the hierarchy. Thus, lexical-semantic fields of sensory verbs are open systems.

Set-aware Entity Synonym Discovery with Flexible Receptive Fields

Entity synonym discovery (ESD) from text corpus is an essential problem in many entity-leveraging applications, e.g., web search and question answering. This paper aims to address three limitations that widely exist in the current ESD solutions: 1) the lack of effective utilization for synonym set information; 2) the feature extraction of entities from restricted receptive fields; and 3) the incapacity to capture higher-order contextual information. We propose a novel set-aware ESD model that enables a flexible receptive field for ESD by making a breakthrough in using entity synonym set information. The contextual information of entities and entity synonym sets are arranged by a two-level network from which entities and entity synonym sets can be mapped into the same embedding space to facilitate ESD by encoding the high-order contexts from flexible receptive fields. Extensive experimental results on public datasets show that our model consistently outperforms the state-of-the-art with significant improvement.

WordNet–ONLINE LEKSIK MA'LUMOTLAR BAZASI

WordNet is a large lexical database of English. Nouns, verbs, adjectives, and suffixes are grouped into a set of cognitive synonyms (syncs), each of which represents a separate concept. Synsets are interconnected using conceptual-semantic and lexical relationships. The resulting network of meaningful words and concepts is managed using a browser. WordNet is also open to the public for download. The WordNet structure is a useful tool fo r the process of computer linguistics and natural languages.

An intent recognition model supporting the spoken expression mixed with Chinese and English

Intent recognition is one of the most essential foundations as well as a very challenging task for language understanding, especially for spoken language. As spoken text is short, and lack of full context. Moreover, it may mix multi-language forms. These non-standard spoken expressions further lead to the shortage of text information. In consideration that sparse text information seriously affects the effect of intention understanding, a multi-feature fusion-based intent recognition model for the bilingual phenomenon mixed with Chinese and English is proposed. Combining word2vec and multilingual wordNets with the same synset_id (synonym set id), the model can mask the differences between different languages. Meanwhile, it can enrich the information representation of the spoken text by fusing the word intention features with the context-dependent features represented by transformer as well as the word frequency features. To verify the correctness and effectiveness of the model, extensive experiments were conducted on a real online logistics customer service platform and SMP2018-ECDT dataset. The results show that our model is superior to other models. And it improves the accuracy of intent recognition in logistics data by 20% compared with that of transformer.

Les vedettes du Dictionnaire Électronique des Synonymes et les relations d’adjacence entre leurs synonymes

The Dictionnaire Électronique des Synonymes of CRISCO (DES, Université de Caen-Normandie) has acquired an undisputed reputation over the last twenty years. The synonymic links that originally originated from 7 source dictionaries have been progressively completed by tens of thousands of proposals from Internet users, whose relevance has been tested and validated by the successive engineers and webmasters of the DES. The present study deals with the utilization of the adjacency graph between all registered synonyms, their distribution into two or more sets of interconnected synonyms, and especially the question of the numerous isolated synonymic links whose integration into an interrelated component is being tested using an original method of exploiting second-order synonymic links. This method, which delivers a high integration rate (between 70% and 80%, irreducible links being removed), will allow an appreciable cleaning of the synonymic network of the DES.

A Link Prediction Approach for Accurately Mapping a Large-scale Arabic Lexical Resource to English WordNet

Success of Natural Language Processing (NLP) models, just like all advanced machine learning models, rely heavily on large -scale lexical resources. For English, English WordNet (EWN) is a leading example of a large-scale resource that has enabled advances in Natural Language Understanding (NLU) tasks such as word sense disambiguation, question answering, sentiment analysis, and emotion recognition. EWN includes sets of cognitive synonyms called synsets, which are interlinked by means of conceptual-semantic and lexical relations and where each synset expresses a distinct concept. However, other languages are still lagging behind in having large-scale and rich lexical resources similar to EWN. In this article, we focus on enabling the development of such resources for Arabic. While there have been efforts in developing an Arabic WordNet (AWN), the current version of AWN has its limitations in size and in lacking transliteration standards, which are important for compatibility with Arabic NLP tools. Previous efforts for extending AWN resulted in a lexicon, called ArSenL, that overcame the size and the transliteration standard limitation but was limited in accuracy due to the heuristic approach that only considered surface matching between the English definitions from the Standard Arabic Morphological Analyzer (SAMA) and EWN synset terms, and that resulted in inaccurate mapping of Arabic lemmas to EWN’s synsets. Furthermore, there has been limited exploration of other expansion methods due to expensive manual validation needed. To address these limitations of simultaneously having large-scale size with high accuracy and standard representations, the mapping problem is formulated as a link prediction problem between a large-scale Arabic lexicon and EWN, where a word in one lexicon is linked to a word in another lexicon if the two words are semantically related. We use a semi-supervised approach to create a training dataset by finding common terms in the large-scale Arabic resource and AWN. This set of data becomes implicitly linked to EWN and can be used for training and evaluating prediction models. We propose the use of a two-step Boosting method, where the first step aims at linking English translations of SAMA’s terms to EWN’s synsets. The second step uses surface similarity between SAMA’s glosses and EWN’s synsets. The method results in a new large-scale Arabic lexicon that we call ArSenL 2.0 as a sequel to the previously developed sentiment lexicon ArSenL. A comprehensive study covering both intrinsic and extrinsic evaluations shows the superiority of the method compared to several baseline and state-of-the-art link prediction methods. Compared to previously developed ArSenL, ArSenL 2.0 included a larger set of sentimentally charged adjectives and verbs. It also showed higher linking accuracy on the ground truth data compared to previous ArSenL. For extrinsic evaluation, ArSenL 2.0 was used for sentiment analysis and showed, here, too, higher accuracy compared to previous ArSenL.

TechWord: Development of a technology lexical database for structuring textual technology information based on natural language processing

The role of text mining based on technological documents such as patents is important in the research field of technology intelligence for technology R&D planning. In addition, WordNet, an English-based lexical database, is widely used for pre-processing text data such as word lemmatization and synonym search. However, technological vocabulary information is complex and specific, and WordNet’s ability to analyze technological information is limited in its reflecting technological features. Thus, to improve the text mining performance of technological information, this study proposes a methodology for designing a TechWord-based lexical database that is based on the lexical characteristics of technological words that are differentiated from general words. To do this, we define TechWord, a technology lexical information, and construct a TechSynset, a synonym set between TechWords. First, through dependency parsing between words, TechWord, a unit word that describes a technology, is structured and identifies nouns and verbs. The importance of connectivity is investigated by a network centrality index analysis based on the dependency relations of words. Subsequently, to search for synonyms suitable for the target technology domain, a TechSynset is constructed through synset information, with an additional analysis that calculates cosine similarity based on a word embedding vector. Applying the proposed methodology to the actual technology-related information analysis, we collect patent data on the technological fields of the automotive field, and present the results of the TechWord and TechSynset. This study improves technological information-based text mining by structuring the word-to-word link information in technological documents based on an automated process.

Development Grouping of Synonym Set Thesaurus Vocabulary The Qur’an in English Using Hierarchical Clustering Algorithm

Research in the field of text mining to process entries or words from the Qur'an is very beneficial for Muslims. This study aims to establish a set of synonyms for the thesaurus in the words of the Qur'an. This research is used because the source of knowledge about the science of the Qur'an is still lacking. The dataset in this study uses the Corpus Qur'an and English Translation. This research is a research development of an article that has been published, namely "The Development of Al-Qur'an Vocabulary Set Synonyms with WordNet Approach" by Laras Gupitasari. Input from this research system uses nouns from the translation of English words in the Quran. The output of the system produces several groups that have the same level of closeness of meaning displayed, the first group means the word in the group has a close meaning. To produce output, this study uses word grouping with a hierarchical grouping method and calculates distances using common paths, then groups results according to the closeness of meaning from word entries. The evaluation in this study produced an F-Measure value of 76%, F-Measure Value is an evaluation to measure the accuracy of predictions issued by the system.

Better to Be Alone than in Bad Company: Cognate Synonyms Impair Word Learning.

The effects of cognate synonymy in L2 word learning are explored. Participants learned the names of well-known concrete concepts in a new fictional language following a picture-word association paradigm. Half of the concepts (set A) had two possible translations in the new language (i.e., both words were synonyms): one was a cognate in participants’ L1 and the other one was not. The other half of the concepts (set B) had only one possible translation in the new language, a non-cognate word. After learning the new words, participants’ memory was tested in a picture-word matching task and a translation recognition task. In line with previous findings, our results clearly indicate that cognates are much easier to learn, as we found that the cognate translation was remembered much better than both its non-cognate synonym and the non-cognate from set B. Our results also seem to suggest that non-cognates without cognate synonyms (set B) are better learned than non-cognates with cognate synonyms (set A). This suggests that, at early stages of L2 acquisition, learning a cognate would produce a poorer acquisition of its non-cognate synonym, as compared to a solely learned non-cognate. These results are discussed in the light of different theories and models of bilingual mental lexicon.

Building Synonym Set for Indonesian WordNet using Commutative Method and Hierarchical Clustering

WordNet is a compilation of Synonyms Set (synset), which consists of the words that have the same synonymous. The development of Indonesian WordNet has a goal to build an application that can accommodate and exhibit the relation of words. Synonym Set is a set composed of one or more words that have a similar meaning or synonym relation originated from the Indonesian Thesaurus. In previous studies, the establishment of synsets were transmitted with several approaches, one of which was the cluster ring to produce synsets and WSD (Word Sense Disambiguation). In this research, research is held up to discover the semantic similarities between words in the Indonesian Thesaurus automatically, and also to know the performance of the Agglomerative Hierarchical Clustering method for the development of Indonesian synsets. To calculate performance and evaluation, this research is using the F-measure method involving the gold standard

Building Synonym Sets for English WordNet with Robust Clustering using Links Method

English WordNet is an important synonym set to present the similarity of meanings between words. Synonym Set is built using Oxford Thesaurus which is accessed through lexico.com, which is a part of the lexical database that will be used. After using the extraction process through Oxford Thesaurus it will produce a synonym set with the same meaning between words. The difference between WordNet and ordinary dictionaries is that the word is interconnected with other words. One method employed for this approach is Robust Clustering Using Links method, which is similarity values and synonym sets that have been created to be used to build a lexical database. Therefore the main purpose of the development of the English WordNet is to produce an accurate synonym set using clustering techniques. The evaluation calculation will use the F-measure method and will use the gold standard for the calculation method. With the ROCK method, there is an increase in accuracy output from dataset input. Building the English wordnet is to improve words that can be used to help research and development of other language wordnets with role models using more accurate English wordnets. And the use of ROCK method there is an increase in the accuracy upon results of the development of English wordnet compared to the previous method, which is using hierarchical clustering. The outcome of this study resulted in improved accuracy so that the ROCK method is one of the good methods used in the development of the English wordnet.

Development Synonym Set for the English Wordnet Using the Method of Comutative and Agglomerative Clustering

Wordnet is a collection of words that interpret or present a meaning, in its development Wordnet has an important part, the Synonym Set or Synset. In making Synonym sets, synonyms are needed and the commutative nature of words is needed. To get word synonyms, the English language thesaurus becomes the reference data for taking synonym data. Broadly speaking, the difference between Wordnet and the dictionary is that the meaning of the word is related to other words, to determine the equation requires a commutative process. The process is made easy by using commutative methods that will produce a candidate synonym set. Candidates for the synonym set cannot be used for word syntax, the grouping process of words which produces the Synonym set as the final result must be carried out. The process of grouping words can one of them use clustering techniques, in this study will use Agglomerative Clustering techniques. In the process of agglomerative clustering techniques there is a threshold value to determine the number of repetitions or as a condition to stop the iteration process. The clustering process in this study will use a threshold value of 0.1 to 1 to test the best threshold value to produce the best Synonym set and calculate its accuracy value. Accuracy calculation and evaluation will use the F-measure method to find the best results.

Building Synsets for Indonesian WordNet using ROCK (Robust Clustering Using Links) Algorithm

On the development of Indonesian WordNet, the synonym set is an important part that represents the similarity of meaning between words. Synonym sets are built using the Indonesian Thesaurus as the lexical database. After going through the extraction process from the Indonesian Thesaurus, we will get a synonym set that has a similarity or word sense between words. In general, the difference between WordNet and the dictionary is their main focus, in which the dictionary usually focuses on just one word, while in WordNet the focus is on the meaning of words and connectedness with other words. Explained in previous research, the constructions of synonym sets were done using several approaches, which is clustering to produce synonym sets and WSD (Word Sense Disambiguation). In this article, the approach used to produce synonym sets is the ROCK (Robust Clustering Using Links) algorithm, which uses similarity and link values. The resulting synonym sets will then be used for lexical database development. Therefore, the main focus of this article is to produce synonym sets through the clustering process and calculate their accuracy, using the F-Measure method involving the gold standard for performance calculation and evaluation.

Microsatellite markers confirm identity of blueberry (Vaccinium spp.) plants in the USDA-ARS National Clonal Germplasm Repository collection

The United States Department of Agriculture (USDA)-Agricultural Research Service (ARS)-National Clonal Germplasm Repository (NCGR) in Corvallis Oregon preserves genetic resources of fruit crops. This genebank contains more than 1800 Vaccinium L. accessions from 34 countries. The genotypic identity of the blueberry cultivars in the NCGR collections is critical to genebank management and operations. Previously, identity confirmation was determined through the morphology of key taxonomic traits, but simple sequence repeat (SSR)-based molecular tools have been developed for more thorough “fingerprinting.” We had previously developed a 5-SSR fingerprinting set of tri-nucleotide-containing SSRs in blueberry. The objectives of this study were to use this 5-SSR blueberry test to compare fingerprints of all plants representing the most requested blueberry cultivars in the screenhouse and field collections of the NCGR; conduct parentage analysis to confirm identity; establish reference fingerprints for these cultivars; and expand the fingerprinting set with additional long core repeats, if needed. The SSR-set distinguished all but ‘Lateblue’ and ‘Berkeley’ and was supplemented with five additional SSRs with long core repeats to generate a 10-SSR fingerprinting set. Genotyping 367 samples with one or both of these SSR sets and parentage analysis where possible detected 54 true-to-type (TTT) cultivars, 13 sets of homonyms and ten groups of synonyms. Parentage analysis identified five of the TTT cultivars among the homonyms (‘Bluecrop’, FL 4B, ‘Nelson’ and ‘Clara’) and ‘Elizabeth’ among the synonym sets. A public database of these reference genetic profiles is available on GRIN-Global. We plan to continue adding to this database and eliminate redundant genotypes for more efficient management of blueberry diversity. Confirmed blueberry genotypes will benefit the germplasm community for use in continued breeding and genetic studies.

Pembangunan Synonym Set Kosa Kata Al-Quran dengan Pendekatan WordNet

Penelitian mengenai Al-Quran di bidang computational linguistics sangat menarik dan bermanfaat apabila dipandang dari seberapa pentingnya Al-Quran bagi umat Islam karena merupakan kitab suci Agama Islam. Dikarenakan saat ini masih kurang akan sumber daya bahasa untuk penelitian Al-Quran, maka penelitian ini bertujuan untuk membangun synonym set Al-Quran yang dapat digunakan sebagai prototype untuk membangun tesaurus Al-Quran. Penelitian ini hanya menggunakan kata benda saja dan pendekatan yang dilakukan yaitu dengan WordNet serta terjemahan Bahasa Inggris Al-Quran. Dalam mengelompokkan kata untuk menghasilkan synonym set penelitian ini menggunakan metode hierarchical clustering. Terakhir, evaluasi hasil synset dilakukan dengan metode F-Measure.

Intelligent Content Conciser using Pointer Generated Network

The combination of best suited architecture and successful algorithm results in the increased nature of efficient learning among the end users. To increase the number of quality learner’s text summarization provides the best initiative among the readers and learners. As words and sentences comprise a document, document summarization finds diverse words with different sets of synonyms by performing training activity for the process. The S2S(Sequence to Sequence) training mechanism describes the embedding way of sentences and documents. The pointer generation enhances the new hybrid model for summary extraction. The proposed model implements attention mechanism and uses Recurrent Neural Network with LSTM cells at encoder and decoder. The working model focuses on many factors for summary extraction such as sentence/document similarity, repeatedness, indexing and sentence-context richness. It also keeps track of summarized text using coverage to avoid repetition.