Synonym Sets Research Articles

Mining Entity Synonyms with Efficient Neural Set Generation

Mining entity synonym sets (i.e., sets of terms referring to the same entity) is an important task for many entity-leveraging applications. Previous work either rank terms based on their similarity to a given query term, or treats the problem as a two-phase task (i.e., detecting synonymy pairs, followed by organizing these pairs into synonym sets). However, these approaches fail to model the holistic semantics of a set and suffer from the error propagation issue. Here we propose a new framework, named SynSetMine, that efficiently generates entity synonym sets from a given vocabulary, using example sets from external knowledge bases as distant supervision. SynSetMine consists of two novel modules: (1) a set-instance classifier that jointly learns how to represent a permutation invariant synonym set and whether to include a new instance (i.e., a term) into the set, and (2) a set generation algorithm that enumerates the vocabulary only once and applies the learned set-instance classifier to detect all entity synonym sets in it. Experiments on three real datasets from different domains demonstrate both effectiveness and efficiency of SynSetMine for mining entity synonym sets.

Corpus-driven Lexical Profiles of the Turkish Synonym Set Sadece, Yalnızca and Yalnız

This is a corpus-driven study based on the TNCv3.0 to identify lexical profiles of the synonym set of Turkish exclusive adverbials sadece, yalnızca and yalnız within the framework of the Model of Extended Lexical Units (Stubbs, 2002). From the concordances of the adverbials, their context-dependent semantic, pragmatic and syntactic properties, co-occurrence tendencies, and synonymity levels were identified. It was found that sadece and yalnızca have a high contextual and collocational equinormality and are completely intersubstitutable and complete synonyms (Lyons, 1981) with yalnızca used less frequently. Yalnız is polysemous and multifunctional and has a sense synonymy relation with the others only when it means only. Even in the sense of only, yalnız was found to be rarely used in certain lexical bundles the other adverbials form. Yalnız was also found to have a topic shifter function. In contexts in which yalnız means only, the three adverbials are cognitive synonyms (Cruse, 1986).

Word Sense Disambiguation Using Cosine Similarity Collaborates with Word2vec and WordNet

Words have different meanings (i.e., senses) depending on the context. Disambiguating the correct sense is important and a challenging task for natural language processing. An intuitive way is to select the highest similarity between the context and sense definitions provided by a large lexical database of English, WordNet. In this database, nouns, verbs, adjectives, and adverbs are grouped into sets of cognitive synonyms interlinked through conceptual semantics and lexicon relations. Traditional unsupervised approaches compute similarity by counting overlapping words between the context and sense definitions which must match exactly. Similarity should compute based on how words are related rather than overlapping by representing the context and sense definitions on a vector space model and analyzing distributional semantic relationships among them using latent semantic analysis (LSA). When a corpus of text becomes more massive, LSA consumes much more memory and is not flexible to train a huge corpus of text. A word-embedding approach has an advantage in this issue. Word2vec is a popular word-embedding approach that represents words on a fix-sized vector space model through either the skip-gram or continuous bag-of-words (CBOW) model. Word2vec is also effectively capturing semantic and syntactic word similarities from a huge corpus of text better than LSA. Our method used Word2vec to construct a context sentence vector, and sense definition vectors then give each word sense a score using cosine similarity to compute the similarity between those sentence vectors. The sense definition also expanded with sense relations retrieved from WordNet. If the score is not higher than a specific threshold, the score will be combined with the probability of that sense distribution learned from a large sense-tagged corpus, SEMCOR. The possible answer senses can be obtained from high scores. Our method shows that the result (50.9% or 48.7% without the probability of sense distribution) is higher than the baselines (i.e., original, simplified, adapted and LSA Lesk) and outperforms many unsupervised systems participating in the SENSEVAL-3 English lexical sample task.

The natural selection of words: Finding the features of fitness.

We introduce a dataset for studying the evolution of words, constructed from WordNet and the Google Books Ngram Corpus. The dataset tracks the evolution of 4,000 synonym sets (synsets), containing 9,000 English words, from 1800 AD to 2000 AD. We present a supervised learning algorithm that is able to predict the future leader of a synset: the word in the synset that will have the highest frequency. The algorithm uses features based on a word’s length, the characters in the word, and the historical frequencies of the word. It can predict change of leadership (including the identity of the new leader) fifty years in the future, with an F-score considerably above random guessing. Analysis of the learned models provides insight into the causes of change in the leader of a synset. The algorithm confirms observations linguists have made, such as the trend to replace the -ise suffix with -ize, the rivalry between the -ity and -ness suffixes, and the struggle between economy (shorter words are easier to remember and to write) and clarity (longer words are more distinctive and less likely to be confused with one another). The results indicate that integration of the Google Books Ngram Corpus with WordNet has significant potential for improving our understanding of how language evolves.

ПАРАДИГМАТИЧЕСКИЙ АСПЕКТ ОБЩЕРУССКОГО СЛОВА В АРХАНГЕЛЬСКИХ ГОВОРАХ

The research is devoted to the consideration of the paradigmatic aspect of All-Russian nouns based on the material of the Arkhangelsk’s sub-dialects. We consider All-Russian nouns with rich polysemy in the Arkhangelsk’s sub-dialects, which have a large number of semantic equivalents in relation to bilateral implication. In lexical synonymy, homonymy of Russian sub-dialects, along with distinctive features, there are many similarities with synonymy, homonymy in the vocabulary of the literary language. It is established that All-Russian nouns have large synonymic series defined by language units, which are in the relationship of semantic juxtaposition. In the dialect system, as well as in the literary language, each lexical meaning has its own set of synonyms, which confirms a certain connection of synonymy with polysemy, in other words, a certain connection between paradigmatic relations and the semantic structure of the word is obvious. It is proved that in the dialect system the synonymic chain expands due to the nominations of species branches. In this study we discover characteristic detailing fixing an object, the phenomenon with a different set of concrete distinctive signs that creates certain conditions for rich synonymy.

Automatic Construction of Persian ICT WordNet using Princeton WordNet

WordNet is a large lexical database of English language, in which, nouns, verbs, adjectives, and adverbs are grouped into sets of cognitive synonyms (synsets). Each synset expresses a distinct concept. Synsets are interlinked by both semantic and lexical relations. WordNet is essentially used for word sense disambiguation, information retrieval, and text translation. In this paper, we propose several automatic methods to extract Information and Communication Technology (ICT)-related data from Princeton WordNet. We, then, add these extracted data to our Persian WordNet. The advantage of automated methods is reducing the interference of human factors and accelerating the development of our bilingual ICT WordNet. In our first proposed method, based on a small subset of ICT words, we use the definition of each synset to decide whether that synset is ICT. The second mechanism is to extract synsets which are in a semantic relation with ICT synsets. We also use two similarity criteria, namely LCS and S3M, to measure the similarity between a synset definition in WordNet and definition of any word in Microsoft dictionary. Our last method is to verify the coordinate of ICT synsets. Results show that our proposed mechanisms are able to extract ICT data from Princeton WordNet at a good level of accuracy.

A New Approach for Calculating Semantic Similarity between Words Using WordNet and Set Theory

Calculating semantic similarity between words is a challenging task of a lot of domains such as Natural language processing (NLP), information retrieval and plagiarism detection. WordNet is a lexical dictionary conceptually organized, where each concept has several characteristics: Synsets and Glosses. Synset represent sets of synonyms of a given word and Glosses are a short description. In this paper, we propose a new approach for calculating semantic similarity between two concepts. The proposed method is based on set theory’s concepts and WordNet properties, by calculating the relatedness between the synsets’ and glosses’s of the two concepts.

АНТОНІМІЧНІ ВІДНОШЕННЯ У ФРАНЦУЗЬКІЙ ФІЗИЧНІЙ ТЕРМІНОСИСТЕМІ

The article addresses the topical issue of antonymy in a terminology system. The author reviews classifications of antonyms based on the semantic and structural criteria. A contrastive analysis of antonymic pairs as an opposition category is performed from the conceptual-semantic perspective. The basis of antonymic relations in a physics terminology system is the semantics of a hypernym term. It determines the extreme hyponym terms through which opposition is realized. It is shown that antonymic pairs in the lexicon of common usage and in a terminology system are not identical. The author posits that this is due to antonymic pairs acquiring new semantic elements while preserving key semantic features present in commonly used words. Antonymic terms in physics can enter into synonymic relations and form synonym sets whose functionality depends on the context of scientific text. Antonyms among physics terms have been divided into contrary (gradual), complementary, and vectorial based by the semantic criterion. The article describes their semantic characteristics and peculiarities of functioning in texts. In particular, contrary antonymic pairs denote two opposite kinds of concepts, between which there are one or more intermediate terms indicating the increase or decrease of a conceptual feature. Complementary antonymy is characterized by the fact that words that are opposed through hyponym terms complement of a single hypernym term and do not contain any intermediate lexical elements. In this kind of antonymy, it is necessary to clearly identify both elements of opposition to avoid ambiguity in the opposition of physical terms. Vector antonymy consist in the opposite of different actions, motions, signs and is quite common in physics terminology.

A diachronic perspective on near-synonymy: The concept of sweet-smelling in American English

AbstractThis paper presents a diachronic analysis of the attributive uses of four synonymous adjectives which designate the concept ofsweet-smelling(fragrant, perfumed, scented, andsweet-smelling) in the latter part of Late Modern and Present-day American English. By drawing on data from theCorpus of Historical American English(COHA) and applying a Hierarchical Configural Frequency Analysis (HCFA), it delineates the internal semantic structure of this set of synonyms, paying special attention to their noun collocates. The results show that the concept ofsweet-smellingexperiences major changes over the time span examined (1850–2009), from being used mostly to qualify entities which can exhibit anaturalpleasant smell (e.g. flowers and trees) to modifying objects which areartificiallysweet-smelling (e.g. oils and shampoos). Moreover,fragrantandperfumed, which initially were the most frequent adjectives, are gradually replaced byscented, thus reflecting a change in the relation between the synonyms over time. The study constitutes the first diachronic approximation to synonymy from the perspective of cognitive semantics and provides equally effective results as previous synchronic research in the field.

СЕМАНТИЧЕСКИЕ ГРУППЫ СЛОВ И СЛОВОСОЧЕТАНИЙ (НА ПРИМЕРЕ АВИАЦИОННОГО АНГЛИЙСКОГО ЯЗЫКА)

The article discusses the vocabulary of aviation English in different semantic groups. The semantic field is allocated; lexico-semantic and thematic groups are revealed. The paper presents synonymic sets and antonymic pairs as well. The author believes that at technical universities it is advisable to study the vocabulary of aviation English systematically to ensure the effective acquisition of these linguistic means. Combining words and phrases into semantic groups will help to systematize the material; the process of the vocabulary memorization will be easy and fast, which will lead to the significant expansion of students’ vocabulary and the formation of the professional foreign language competence of future aviation specialists.

AUTHOR’S NEOLOGISMS IN OLES HONCHAR’S LEXICON

The article deals with the lexicon of Oles Honchar’s literary works and author’s neologisms denoting static characteristics of objects. Author’s neologisms are classified to thematic groups and synonymic sets; their stylistic functions are analyzed. In the works of Oles Honchar, author's neologisms are complex in structure. Their semantic expressiveness is based on word-forming and semantic resources of the language. Most of the occasional neologisms are represented in the thematic group of nominations for the light-color spectrum. These neologisms function in texts as epithets, metaphors, symbols. Occasional neologisms in thematic groups illustrate their number, structure, relationship within the theme, semantics, associations. The findings presented in the article can be used for compiling Honchar’s vocabulary.

A corpus study of Chinese EFL learners’ use of circumstance, demand, and significant

Abstract This study investigated Chinese EFL learners’ use of circumstance, demand, and significant, three challenging words each being a member in a synonym set: circumstance in the case/circumstance/event/situation set, demand in the ask/demand/request/require set, and significant in the important/meaningful/significant set. Via an expert rating and a close examination of all the uses of the three words in Wen, Wang, and Liang’s (2005) Spoken and Written English Corpus of Chinese Learners, the study has uncovered various inappropriate usages as well as successfully acquired usages involving the three words. The results reveal a failure by many Chinese EFL learners to understand the three words’ semantic usage differences with their respective synonyms. The study has also identified L1 interference, inadequate descriptions of these words in dictionaries, and insufficient instructional attention to the semantic usage differences among synonyms as likely reasons for the learners’ inappropriate usages. Pedagogical and research implications are also discussed.

СИНОНИМЫ КАК СРЕДСТВО РЕПРЕЗЕНТАЦИИ ПРИЗНАКА «ТЯЖЕЛЫЙ» В АНГЛИЙСКОМ ЯЗЫКЕ

The article analyzes the nominations of the attribute “heavy” with English adjectives implemented in authentic texts and recorded in lexicographic sources. The result of the study is the description of the semantic links of the synonyms that determine the content of the attribute “heavy” in the minds of native speakers. The novelty consists in the identification of the conceptual characteristics, in accordance with which synonymic sets are formed, as well as in determining the national specificity of the use of the adjectives representing the attribute “heavy” in the English language.

WSD algorithm based on a new method of vector-word contexts proximity calculation via epsilon-filtration

The problem of word sense disambiguation (WSD) is considered in the article. Given a set of synonyms (synsets) and sentences with these synonyms. It is necessary to select the meaning of the word in the sentence automatically. 1285 sentences were tagged by experts, namely, one of the dictionary meanings was selected by experts for target words. To solve the WSD-problem, an algorithm based on a new method of vector-word contexts proximity calculation is proposed. In order to achieve higher accuracy, a preliminary epsilon-filtering of words is performed, both in the sentence and in the set of synonyms. An extensive program of experiments was carried out. Four algorithms are implemented, including a new algorithm. Experiments have shown that in a number of cases the new algorithm shows better results. The developed software and the tagged corpus have an open license and are available online. Wiktionary and Wikisource are used. A brief description of this work can be viewed in slides (https://goo.gl/9ak6Gt). Video lecture in Russian on this research is available online (https://youtu.be/-DLmRkepf58).

Calculating Similarity of Curriculum Lattes

This paper implements a similarity algorithm that calculates the percentage of adhesion between academic profile of the University of Brasilia. The supplier base field of data that makes possible the calculation will be the Lattes Platform. This offers the information of academic literature production registered members. The calculation shows the classification of the individuals and the similarities between their academic productions. This is achieved by considering a profile basis compared to one or more destination profiles. To perform this procedure, the information is extracted from each curriculum Lattes, created ontology of concepts that contain data pertaining to production to provide subsidy to comparisons. These comparisons are performed in each term of the names of all the literature production of both profiles compared. Each term can contain a set of synonyms which are also considered in the comparison. The results are compiled and presented in a spreadsheet that contains the summaries of all the percentage of adhesion compared. The application of the algorithm which determines a set of people has more or less proximity and semantic link according to their academic productions when compared with other individuals, resulting in the percentage of similarity.

ПРОБЛЕМЫ СОСТАВЛЕНИЯ АНТОНИМО-СИНОНИМИЧЕСКИХ ПАРАДИГМ КОМПОЗИТОВ

The article is devoted to the problems of composing antonymic-synonymic paradigms of compound words. The author shows the algorithm for constructing antonymic-synonymic paradigms, the principles of choosing the dominant and compiling the main sets of synonyms and antonymic pairs in word groups of related semantics. Basing on the method of vocabulary definitions and a component analysis, the status of invariant and differential semes is determined. The paper considers the variants of classifying the same composites to different antonymic-synonymic groups. The factors complicating the structuring of antonymic-synonymic paradigms are revealed.

A Word-Embedding-Based Steganalysis Method for Linguistic Steganography via Synonym Substitution

The development of steganography technology threatens the security of privacy information in smart campus. To prevent privacy disclosure, a linguistic steganalysis method based on word embedding is proposed to detect the privacy information hidden in synonyms in the texts. With the continuous Skip-gram language model, each synonym and words in its context are represented as word embeddings, which aims to encode semantic meanings of words into low-dimensional dense vectors. The context fitness, which characterizes the suitability of a synonym by its semantic correlations with context words, is effectively estimated by their corresponding word embeddings and weighted by TF-IDF values of context words. By analyzing the differences of context fitness values of synonyms in the same synonym set and the differences of those in the cover and stego text, three features are extracted and fed into a support vector machine classifier for steganalysis task. The experimental results show that the proposed steganalysis improves the average F-value at least 4.8% over two baselines. In addition, the detection performance can be further improved by learning better word embeddings.

НОМІНАТИВНЕ ПОЛЕ СУБКОНЦЕПТУ SANITAS В ЛАТИНСЬКІЙ МОВІ

The article is devoted to the investigation of the nominative field of the subconcept SANITAS in the Latin language, which has a complex character due to the integration in its structure lexical field, phraseological field and synonymic sets. The essence of the nominative field in the system of language has been analyzed with regard to the specifics of nominative units – its verbalizers; kernel and prekernel zones, near and far peripheries have been defined; the means of microfields verbalization of the prekernel zone of subconcept SANITAS as well as the list of lingual units verbalizing the concept HEALTH have been investigated. It has been defined that nominative field structure of the HEALTH concept is represented as core and pre-core zones consisting of some microfields as well as close and distant peripheries of SALUS, SANITAS, VALETUDO subconcepts. The semantic field of the SANITAS subconcept has been built up due to the principle of semantic proximity / difference basing on the integral seme and frequency of acquiring certain meanings by the concepts’ names. It has been defined that the SALUS, SANITAS, VALETUDO subconcepts share the common slots «being (somatically and/or mentally) healthy» and «providing somatic and/or mental health». It has also been emphasized that the SANITAS subconcept substantially integrated the semes of HEALTH concept that led to its dominant role in nominating both somatic and mental health states in the lingual world model of the ancient Romans, while the sanitas lexeme and co-root words appear to be the fundamental means that verbalize the HEALTH concept in the Latin language. Therefore, the article contributes to the development of the theoretical principles of ancient languages concepts’ research as well as to the development of cognitive linguistics, linguistic culturology, axiological linguistics, etc. It enables to find out the specific dimensions of ancient Romans’ mode of thinking and their world outlook.

Simplifying drug package leaflets written in Spanish by using word embedding

BackgroundDrug Package Leaflets (DPLs) provide information for patients on how to safely use medicines. Pharmaceutical companies are responsible for producing these documents. However, several studies have shown that patients usually have problems in understanding sections describing posology (dosage quantity and prescription), contraindications and adverse drug reactions. An ultimate goal of this work is to provide an automatic approach that helps these companies to write drug package leaflets in an easy-to-understand language. Natural language processing has become a powerful tool for improving patient care and advancing medicine because it leads to automatically process the large amount of unstructured information needed for patient care. However, to the best of our knowledge, no research has been done on the automatic simplification of drug package leaflets. In a previous work, we proposed to use domain terminological resources for gathering a set of synonyms for a given target term. A potential drawback of this approach is that it depends heavily on the existence of dictionaries, however these are not always available for any domain and language or if they exist, their coverage is very scarce. To overcome this limitation, we propose the use of word embeddings to identify the simplest synonym for a given term. Word embedding models represent each word in a corpus with a vector in a semantic space. Our approach is based on assumption that synonyms should have close vectors because they occur in similar contexts.ResultsIn our evaluation, we used the corpus EasyDPL (Easy Drug Package Leaflets), a collection of 306 leaflets written in Spanish and manually annotated with 1400 adverse drug effects and their simplest synonyms. We focus on leaflets written in Spanish because it is the second most widely spoken language on the world, but as for the existence of terminological resources, the Spanish language is usually less prolific than the English language. Our experiments show an accuracy of 38.5% using word embeddings.ConclusionsThis work provides a promising approach to simplify DPLs without using terminological resources or parallel corpora. Moreover, it could be easily adapted to different domains and languages. However, more research efforts are needed to improve our approach based on word embedding because it does not overcome our previous work using dictionaries yet.

The Missing Style Problem and the Translation of French Erotica into English

In most synonym sets, there is a neutral item that does not belong to any particular style (poor is neutral whereas impecunious and broke are not). In writings about sex, French has a neutral style but English does not. The English translations of two French autobiographies detailing the authors’ sex lives are presented and some of the translators’ strategies are discussed. These two cases are seen against the general background of style options available to translators. A translator’s approach to style can be theorized by comparison to the source text (use an equivalent style, use a different existing style, create a new style, use a default ‘translating style’) or by considering how the translator ‘voices’ the translation (use the voice of the source writer, the imagined future readers, the translator, or some other voice).