Polysemous Words Research Articles

Polysemy in Modern English Pump Engineering Terminology

. This article focuses on the problem of polysemy in modern English terminology within the special subsystem of terms – pump engineering. A polysemantic lexical unit has a hierarchically organized structure of meanings. It consists of indivisible elementary semantic units and they are realized simultaneously in each context. The lexical units of the pump engineering terminological subsystem fulfill the requirements for terms. However, this subsystem terminology is not free from polysemy, which is considered undesirable for terminological vocabulary. The polysemantic terms make up 71.9% of the terminological units in our sample. Some pump engineering terms do not have clearly defined semantic boundaries and they enter into semantic relationships with other terms. Sometimes terminological units correspond to two or more different concepts, realizing several related meanings. Metonymy is the primary source of polysemy in the pump engineering subsystem. The metonymic transfer is carried out by transferring the name of a machine, device, tool to the worker who uses them, conveying the name of the whole to parts, transferring the name of a part to a whole, transferring the general name of a technical process to its components. With the ambiguity arising from the metonymic transfer, the connections between the polysemantic word meanings are understandable and visible. Different meanings of the same word complement each other, while each meaning illuminates the characteristics of different objects in its own way. Usually it is possible to trace the relationship between the various definitions of the polysemantic unit of pump engineering .

Adaptive and hybrid context-aware fine-grained word sense disambiguation in topic modeling based document representation

We propose a hybrid context based topic model with an adaptive context window length for word sense disambiguation in document representation. Document representation is an essential part of various document based tasks, and word sense disambiguation is to capture the distinctions of word senses in the representation. Traditional methods mainly rely on knowledge libraries for data enrichment; however, semantics division for a word may vary in different domain-specific datasets. We aim to discover finer-grained word semantic differences, such as different entities or standpoints, and handle the disambiguation problem without data enrichment. There are two challenges for this disambiguation task: (1) dividing various senses for each polysemous word, and (2) preserving the differences between synonyms. Most of the existing models are either based on separate context clusters or integrating an auxiliary module to specify word senses. They can hardly achieve both (1) and (2) since different senses of a word are assumed to be independent and their intrinsic relationships are ignored. To solve this problem, we introduce the “Bag-of-Senses” (BoS) assumption: a document is a multiset of word senses, and the senses are generated instead of the words. The word senses are estimated by both the context in which it occurs and the contexts of its other occurrences. Besides, to handle the different scopes of the sense related context to each word occurrence, we introduce a variable to adjust the context window length adaptively. Our experiments on three standard datasets show that our proposal outperforms other state-of-the-art methods in terms of word sense estimation, topic modeling, and document classification.

Prashant Pardeshi, Yosuke Momiyama, Yuriko Sunakawa, Shingo Imai, and Yasunari Imamura: Tagidōshi-bunseki no shin-tenkai to nihongo-kyōiku eno ōyō [New developments in the analysis of polysemous words and their application to Japanese language education

Article Prashant Pardeshi, Yosuke Momiyama, Yuriko Sunakawa, Shingo Imai, and Yasunari Imamura: Tagidōshi-bunseki no shin-tenkai to nihongo-kyōiku eno ōyō [New developments in the analysis of polysemous words and their application to Japanese language education] was published on May 1, 2021 in the journal Journal of Japanese Linguistics (volume 37, issue 1).

Word Senses as Clusters of Meaning Modulations: A Computational Model of Polysemy.

Most words in natural languages are polysemous; that is, they have related but different meanings in different contexts. This one-to-many mapping of form to meaning presents a challenge to understanding how word meanings are learned, represented, and processed. Previous work has focused on solutions in which multiple static semantic representations are linked to a single word form, which fails to capture important generalizations about how polysemous words are used; in particular, the graded nature of polysemous senses, and the flexibility and regularity of polysemy use. We provide a novel view of how polysemous words are represented and processed, focusing on how meaning is modulated by context. Our theory is implemented within a recurrent neural network that learns distributional information through exposure to a large and representative corpus of English. Clusters of meaning emerge from how the model processes individual word forms. In keeping with distributional theories of semantics, we suggest word meanings are generalized from contexts of different word tokens, with polysemy emerging as multiple clusters of contextually modulated meanings. We validate our results against a human-annotated corpus of polysemy focusing on the gradedness, flexibility, and regularity of polysemous sense individuation, as well as behavioral findings of offline sense relatedness ratings and online sentence processing. The results provide novel insights into how polysemy emerges from contextual processing of word meaning from both a theoretical and computational point of view.

A BERT based Chinese Named Entity Recognition method on ASEAN News

As the first step of building a knowledge graph to record the ASEAN counties’ information, we aim to conduct Named-entity Recognition (NER) on the Chinese news about ASEAN counties. We employ a Bi-directional gated recurrent unit to replace the LSTM architecture to improve both models’ effectiveness and capability in understanding polysemous words. The state-of-the-art word embedding model, BERT, has also been included to generate qualified word vectors for the NER task. Besides, we also propose a similarity-based dataset partition method to help model learning the polysemy within the Chinese news. Experiments have been done to demonstrate that the combination of such improvements can benefit the models’ performance in identifying different types of named entities.

현대중국어 ‘一定’의 의미 기능 및 공기 성분 연구

This paper examines the semantic functions of ‘Yiding(一定)’ in Mandarin Chinese, and analyzes the characteristics of VP that co-occurs with ‘Yiding(一定)’.<BR> First, divides the semantic functions of the polysemous word ‘Yiding(一定)’ into three: ‘presume’, ‘intensify’, and ‘promise’. In usage, it is found that when ‘Yiding(一定)’ expresses ‘intensify’, auxiliary verbs need to appear together or be used in imperative sentences. To express the ‘promise’ function requires the speaker and the acting subject to be consistent. If this condition is met, the subject can be the first person or the third person, and even the subject is allowed to not appear.<BR> Second, by investigating the actual corpus, it is found that when expressing the three semantic functions of ‘Yiding(一定)’, there is a restriction on the choice of co-occurring VP. If the VP contains aspect marks and the main predicate in the VP are ‘Shi(是), You(有), adjective’ or ‘combinatorial predicate-complement’, then ‘Yiding(一定)’ expresses the epistemic modality of ‘presume’ semantics; If the VP contains the deontic modal verbs ‘Yao(要), Dei(得)’, then ‘Yiding(一定)’ expresses the non-modality that ‘intensify’ the semantics; If VP contains the auxiliary verb ‘Hui(会)’, ‘Yiding(一定)’ expresses the epistemic modality, and the first-person subject will express the deontic modality of ‘promise’ semantics.

Embodying Pre-Trained Word Embeddings Through Robot Actions

We propose a promising neural network model with which to acquire a grounded representation of robot actions and the linguistic descriptions thereof. Properly responding to various linguistic expressions, including polysemous words, is an important ability for robots that interact with people via linguistic dialogue. Previous studies have shown that robots can use words that are not included in the action-description paired datasets by using pre-trained word embeddings. However, the word embeddings trained under the distributional hypothesis are not grounded, as they are derived purely from a text corpus. In this letter, we transform the pre-trained word embeddings to embodied ones by using the robot's sensory-motor experiences. We extend a bidirectional translation model for actions and descriptions by incorporating non-linear layers that retrofit the word embeddings. By training the retrofit layer and the bidirectional translation model alternately, our proposed model is able to transform the pre-trained word embeddings to adapt to a paired action-description dataset. Our results demonstrate that the embeddings of synonyms form a semantic cluster by reflecting the experiences (actions and environments) of a robot. These embeddings allow the robot to properly generate actions from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$unseen$</tex-math></inline-formula> <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$words$</tex-math></inline-formula> that are not paired with actions in a dataset.

Analysis of Vocabulary Definitions of the Word “Uspech” (“Success”): Problem of Verification of Linguoculturological Constructions

A method for solving the actual problem of verification of linguocultural constructions is proposed. Attention is paid to the establishment of the correctness and effectiveness of the application of one of the types of semantic analysis in modern linguistic studies devoted to the concept of “success” and its lexical representatives. The proposed meta-research approach is aimed at identifying and searching for the causes of significant discrepancies in the results of definitional analysis when the theoretical base, scientific apparatus and research strategy coincide. This approach allows the author to consider a number of controversial cases of the use of definitional analysis associated with its object, subject and metalanguage, and to solve some important methodological issues: what kind of linguistic sources are involved in collecting material; how the definitional analysis of a polysemantic word is carried out; in what aspect the interlingual comparison of the dictionary definitions of one word is carried out; what advantages and disadvantages of different formats for describing semantic components are identified as a result of definitional analysis, etc. Critical analysis of research techniques alternates with constructive sentences for the semantic analysis of the dictionary definitions of the word success in modern Russian. General observations on the features of the application of the analytical method under consideration are proposed as conclusions.

Adaptive cross-contextual word embedding for word polysemy with unsupervised topic modeling

Because of its efficiency, word embedding has been widely used in many natural language processing and text modeling tasks. It aims to represent each word by a vector so such that the geometry between these vectors can capture the semantic correlations between words. An ambiguous word can often have diverse meanings in different contexts, a quality which is called polysemy. The bulk of studies aimed to generate only one single embedding for each word, whereas a few studies have made a small number of embeddings to present different meanings of each word. However, it is hard to determine the exact number of senses for each word, as meanings depend on contexts. To address this problem, this paper proposes a novel adaptive cross-contextual word embedding (ACWE) method for capturing the word polysemy in different contexts based on topic modeling, in which the word polysemy is defined over a latent interpretable semantic space. The proposed ACWE consists of two main parts, in the first of which an unsupervised cross-contextual probabilistic word embedding model is designed to obtain the global word embeddings, and each word is represented by an embedding in the unified latent semantic space. Based on the global word embeddings, an adaptive cross-contextual word embedding process is then devised in the second part to learn the local embeddings for each polysemous word in different contexts. In fact, a word embedding is adaptively adjusted and updated with respect to different contexts to generate different word embeddings tailored to the corresponding contexts. The proposed ACWE is validated on two datasets collected from Wikipedia and IMDb on different tasks including word similarity, polysemy induction, semantic interpretability, and text classification. Experimental results indicate that ACWE does not only outperform the established word embedding methods, which consider word polysemy on six popular benchmark datasets, but it also yields competitive performance compared with state-of-the-art deep learning-based approaches without considering polysemy. Moreover, the proposed ACWE significantly improves the performances of text classification both in precision and F1, and the visualizations of the semantics of words demonstrate the feasibility and advantage of the proposed ACWE model on polysemy.

A sentiment-aware deep learning approach for personality detection from text

Personality detection based on user-generated text content analysis has a significant impact on information science, for instance, information seeking. Existing deep learning-based approaches, however, have two major limitations. Firstly, they extract only keywords for personality detection and lack the analysis of sentiment information and psycholinguistic features. Secondly, the information about the context and polysemous words are ignored. To tackle these problems, we propose a novel multi-label personality detection model based on neural networks, which combines emotional and semantic features. Specifically, we leverage Bidirectional Encoder Representation from Transformers (BERT) to generate sentence-level embedding for text semantic extraction. In addition, a sentiment dictionary is used for text sentiment analysis in order to consider sentiment information. Finally, we input the above semantic information and emotional information into the neural network to construct an automatic personality detection model. The performance of the model has been evaluated on two public personality datasets. The experiments show that we obtain average accuracy improvements of 6.91% and 6.04% on the Myers-Briggs Type Indicator (MBTI) and Big Five datasets, respectively, compared with the state-of-the-art techniques.

Kinds of Meaning in Classical Arabic from More Recent Denotational Theory Perspectives

This paper explores the extent to which meaning is conveyed in Classical Arabic. It aims to quantify as well as qualify the various kinds of meaning and the techniques used to advance them on the linguistic various levels. From a semantic perspective, it first categorizes kinds of meaning according to denotation and connotations satisfied by paraphrasing and definition and to 'sense' perceived by ostensive, i.e. sensory, definition. Second, it examines the syntactic meaning achieved by composition, addition, and (inclusively but exceptionally by) Arabic sentence-pattern switching and phoneme clipping on the structural level. Then, it advances lexical meaning expressed by synonyms, antonyms, hyponyms, meronyms, polysemous words, and family resemblances. Finally, it presents the categorematic word that can carry full meaning and the syncategorematic one which can only modify meaning. In both types, morphemes are isolated and allomorphs are exemplified. The paper quotes from the Holy Script of Islam, the Noble Quran, for its linguistic preciseness and conciseness.

Intelligent Recognition and Teaching of English Fuzzy Texts Based on Fuzzy Computing and Big Data

In this paper, we conduct in‐depth research and analysis on the intelligent recognition and teaching of English fuzzy text through parallel projection and region expansion. Multisense Soft Cluster Vector (MSCVec), a multisense word vector model based on nonnegative matrix decomposition and sparse soft clustering, is constructed. The MSCVec model is a monolingual word vector model, which uses nonnegative matrix decomposition of positive point mutual information between words and contexts to extract low‐rank expressions of mixed semantics of multisense words and then uses sparse. It uses the nonnegative matrix decomposition of the positive pointwise mutual information between words and contexts to extract the low‐rank expressions of the mixed semantics of the polysemous words and then uses the sparse soft clustering algorithm to partition the multiple word senses of the polysemous words and also obtains the global sense of the polysemous word affiliation distribution; the specific polysemous word cluster classes are determined based on the negative mean log‐likelihood of the global affiliation between the contextual semantics and the polysemous words, and finally, the polysemous word vectors are learned using the Fast text model under the extended dictionary word set. The advantage of the MSCVec model is that it is an unsupervised learning process without any knowledge base, and the substring representation in the model ensures the generation of unregistered word vectors; in addition, the global affiliation of the MSCVec model can also expect polysemantic word vectors to single word vectors. Compared with the traditional static word vectors, MSCVec shows excellent results in both word similarity and downstream text classification task experiments. The two sets of features are then fused and extended into new semantic features, and similarity classification experiments and stack generalization experiments are designed for comparison. In the cross‐lingual sentence‐level similarity detection task, SCLVec cross‐lingual word vector lexical‐level features outperform MSCVec multisense word vector features as the input embedding layer; deep semantic sentence‐level features trained by twin recurrent neural networks outperform the semantic features of twin convolutional neural networks; extensions of traditional statistical features can effectively improve cross‐lingual similarity detection performance, especially cross‐lingual topic model (BL‐LDA); the stack generalization integration approach maximizes the error rate of the underlying classifier and improves the detection accuracy.

Methods for determining homonyms in homonymy and linguistic systems

As you know, homonymous lexemes differ from polysemous words. Polysemantic words have semantic or formal connections, and homonymous tokens are monosyllabic words with different meanings. Both phenomena are considered an urgent problem in the linguistic processing of texts. In particular, the definition of homonymy is important for translation and analysis in Natural Language Processing (NLP). This article discusses several ways to identify and analyze homonymous forms in Uzbek texts using word combination models.

Sentiment analysis of MOOC reviews via ALBERT-BiLSTM model

The accurate exploration of the sentiment information in comments for Massive Open Online Courses (MOOC) courses plays an important role in improving its curricular quality and promoting MOOC platform’s sustainable development. At present, most of the sentiment analyses of comments for MOOC courses are actually studies in the extensive sense, while relatively less attention is paid to such intensive issues as the polysemous word and the familiar word with an upgraded significance, which results in a low accuracy rate of the sentiment analysis model that is used to identify the genuine sentiment tendency of course comments. For this reason, this paper proposed an ALBERT-BiLSTM model for sentiment analysis of comments for MOOC courses. Firstly, ALBERT was used to dynamically generate word vectors. Secondly, the contextual feature vectors were obtained through BiLSTM pre-sequence and post-sequence, and the attention mechanism that could calculate the weight of different words in a sentence was applied together. Finally, the BiLSTM output vectors were input into Softmax for the classification of sentiments and prediction of the sentimental tendency. The experiment was performed based on the genuine data set of comments for MOOC courses. It was proved in the result that the proposed model was higher in accuracy rate than the already existing models.

Children make use of relationships across meanings in word learning.

Many words are associated with more than a single meaning. Words are sometimes "ambiguous," applying to unrelated meanings, but the majority of frequent words are "polysemous" in that they apply to multiple related meanings. In a preregistered design that included 2 tasks, we tested adults' and 4.5- to 7-year-old children's ability to learn 4 novel polysemous words or 4 novel ambiguous words. Both children and adults demonstrated a polysemy over ambiguity learning advantage on each task after exposure, showing better learning of novel words with multiple related meanings than novel words with unrelated meanings. Stimuli in the polysemy condition were designed and then normed to guard against learners relying on a simple definition to distinguish the multiple target meanings for each word from foils. We retested available participants after a week-long delay without providing additional exposure and found that adults' performance remained strong in the polysemy condition in 1 task, and children's performance remained strong in the polysemy condition in both tasks. We conclude that participants are adept at learning polysemous words that vary along multiple dimensions. Current results are consistent with the idea that ambiguous meanings of a word compete, but polysemous meanings instead reinforce one another. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

МНОГОУРОВНЕВАЯ СТРУКТУРА ПОЛИСЕМАНТА: ИНВАРИАНТНО-КЛАСТЕРНЫЙ АНАЛИЗ

Within the framework of the article, we have come up with a hypothesis of a polysemous word integrity as a multilevel structure, which is ensured by the dominant lexical invariant meaning. The analysis of the English polysemous word “key” is presented with the use of the empirical invariant-component method. Metaphorical clusters of meanings of this word and its lexical invariant are defined as a set of basic dominant components that form the semantic core of the word. The reasons for the ambiguity of the boundaries of the lexical meaning are substantiated, the patterns of schematization of the meanings of the word “key” are revealed. The use of lexical invariants can be useful for didactic purposes when using them as an alternative to memorizing lists of polysemous word meanings. The proposed method can be useful when compiling educational dictionaries. The representation of the semantic structure of words in the form of lexical invariants has a number of advantages over the “list theory”, it can significantly complement the theory of “general meaning”.

Semantic core of polysemic structure, its internal sources realization in terminological systems functioning

The phenomenon of polysemic word and term core semantic invariant is investigated in the article. The structure of the mentioned phenomenon features conceptional complicity, multiple levels along with explicit and implicit distinctive semantic components synthesis. One of the distinctive features of semantic invariant core is its connection with the system of connotative semantic components. One of the attributes of this system is complex gradation of connotative intensity degrees. This structure consists of many semantic levels while invariant core functioning depends on the influence of not only separate semantic components but also the entire invariant model. The model is considered to be an integrated semantic complex. Semantic invariant core functioning has been analyzed with regard to the changing of different semantic, including terminological, fields processes. Changing of semantic bases as well as semantic opposition components has also been examined. Moreover, we have researched the processes of semantic categories emergence, actualization and alternation in the polysemic word semantic structure. Furthermore, the phenomenon of categorial and integral features interconnection in semantic invariant structure has been observed. We believe that such processes analysis requires research of diachronic along with synchronic word functioning aspects. Semantic invariants’ conceptual structure causes semantic cores functioning both in all discourse types and interlinguistic phenomena as well as processes, including semantic linguistic conversion phenomema, metaphorical processes, transterminologisation. Semantic and conceptional variability of paradigmatic relations in the invariant structure has been revealed. This variability is an essential condition for existence of common, terminological lexis and polysemy. Dynamism is one of the key peculiarities of semantic invariant potential. One of the semantic invariant main features is the unity of invariability and potential possibility of constant development.

ПОРІВНЯННЯ МОЖЛИВОСТЕЙ ЗАСТОСУВАННЯ КОНТЕКСТУАЛЬНОГО МЕТОДУ ПРИ ВИВЧЕННІ ЛЕКСИКОЛОГІЇ ТУРЕЦЬКОЇ ТА АНГЛІЙСЬКОЇ МОВИ

The relevance of the English Language learning is substantiated in the article for many reasons. First, because of its prevalence in the whole world. Secondly, due to the huge number of lexical and stylistic features, such as context, polysemantic words, direct word order in sentence, variability (British, American, Canadian, Australian, New Zealand English). Thirdly, owing to its clarity, conciseness, emotional colouring and individuality. The article defines the possibilities of the contextual method using in the Turkish and English language Lexicology studying. Such teaching methods as descriptive (for a general description of the context); contextual-interpretive (to identify the functional and semantic meaning of a word), as well as a method of creating a problem situation using a contextual task were used for achieving the goal. The features of the English language as the language of international communication are determined; the place of the context in English is considered and the role of the English context in comparison with the Turkish one is defined. The difficulties of translating words from English and vice versa due to their ambiguity are stipulated. Especially it concerns synonymic dominants, idioms, set phrases and phrasal verbs. Context has been shown to understand the meaning of a word or phrase. Depending upon the context and lexical surroundings, most words in common vocabulary can change their meaning in both Turkish and English.

Peculiarities of using anglicisms in the texts of regional news

The article is devoted to the problem of using English borrowings in the texts of Ukrainian regional news and their influence on the use of regional dialects in everyday speech. In addition, in this article, the concept of “anglicism” is revealed, and the main reasons for the presence of anglicisms in regional news are explained. On the basis of regional news, the most commonly used English borrowings are identified, and illustrations of their use in news articles are provided. Because of the descriptive and comparative methods, the peculiarities of the use of foreign borrowings in news texts are analyzed. The given article provides the possible Ukrainian dialect equivalents for popular anglicisms. On the basis of the general regionally annotated corpus of the Ukrainian language, the most common Ukrainian words with which anglicisms are combined (on the basis of the newspaper “Vysokyi Zamok”) were studied. It is established that it can be the combinations with adjectives and verbs or with proper names. In the process of analyzing the selected English borrowings, the main semantic changes to which these lexical units are subjected are characterized. Since most of the borrowings are polysemantic words, they often change their meaning in the process of adaptation to the lexical-semantic system of the Ukrainian language. Anglicisms are subjected to such semantic changes as the expansion, contraction and preservation of the meaning of the word. In order to fully characterize the changes in the meaning of the word, the article presents the definitions recorded in the dictionaries of English and Ukrainian languages and compares them with the meanings in which English borrowings are used in regional news. Examples of anglicisms with extended and narrowed semantics and those that do not change their meaning in the process of borrowing, are provided. Considering of the problem regarding the emergence of anglicisms in news texts is relevant today, taking into account the rapid development of Ukraine in international relations.

Linguistic Steganalysis With Graph Neural Networks

Recent linguistic steganalysis methods model texts as sequences and use deep learning models to extract discriminative features for detecting the presence of secret information in texts. However, natural language has a complex syntactic structure and sequences have limited representation ability for text modeling. Moreover, previous methods tend to extract features from local continuous word sequences, which cannot effectively model global characteristics. In this paper, we present a linguistic steganalysis method with graph neural network. In the proposed method, texts are translated as directed graphs with the associated information, where nodes denote words and edges show associations between the words. By training a graph convolutional network for feature extraction, each node of a graph can collect contextual information to update self-expression, accordingly effectively solving the problem of poor representation of polysemous words. Meanwhile, we adopt a globally-shared matrix to record correlation strengths between words so that each text can effectively utilize the global information to obtain the better self-representation. Experimental results have shown that the proposed work achieves the state-of-the-art performance comparing with the previous works.