Features Of Words Research Articles

Identification of offensive language in Urdu using semantic and embedding models.

Automatic identification of offensive/abusive language is very necessary to get rid of unwanted behavior. However, it is more challenging to generalize the solution due to the different grammatical structures and vocabulary of each language. Most of the prior work targeted western languages, however, one study targeted a low-resource language (Urdu). The prior study used basic linguistic features and a small dataset. This study designed a new dataset (collected from popular Pakistani Facebook pages) containing 7,500 posts for offensive language detection in Urdu. The proposed methodology used four types of feature engineering models: three are frequency-based and the fourth one is the embedding model. Frequency-based are either determined by the term frequency-inverse document frequency (TF-IDF) or bag-of-words or word n-gram feature vectors. The fourth is generated by the word2vec model, trained on the Urdu embeddings using a corpus of 196,226 Facebook posts. The experiments demonstrate that the stacking-based ensemble model with word2vec shows the best performance as a standalone model by achieving 88.27% accuracy. In addition, the wrapper-based feature selection method further improves performance. The hybrid combination of TF-IDF, bag-of-words, and word2vec feature models achieved 90% accuracy and 97% AUC. In addition, it outperformed the baseline with an improvement of 3.55% in accuracy, 3.68% in the recall, 3.60% in f1-measure, 3.67% in precision, and 2.71% in AUC. The findings of this research provide practical implications for commercial applications and future research.

Taqlid soʻzlarning oʻrganilish darajasi va tasniflanish tamoyillari

The purpose of the article is to identify the typological features of modern English and Uzbek imitative words, semantic and contextual description, showing the norm of constant use, translation problems.The morphological, semantic and typological-structural state of mimetic expressions in modern English and Uzbek languages and the problems of mutual translation are highlighted in the research. In Uzbek, imitative words are morphologically divided into separate word groups between independent and non-independent word groups, while in English linguistics, imitative words and independent words formed from imitation are called onomatopeia. However, it was found that the independent words made from imitation in the morphological layer belong to one of the existing independent word groups according to their grammatical signs. Also, the disadvantages of translating imitative words from Uzbek to English, from English to Uzbek, including imitative words can be omitted in the translation text or expressed by transliteration.

An approach for radical innovative design based on cross-domain technology mining in patents

The key to radical innovation lies in technological breakthroughs, and the key to technical breakthroughs lies in the application of cross-domain knowledge. However, in the conceptual design stage of new product development, the designer’s cognition and knowledge are limited and the retrieval and evaluation of cross-domain technologies is often subjective, making it difficult to generate radical concepts. To address the above issues, this paper proposes a method for cross-domain technology recommendation based on patent analysis. In this method, feature words in various domains of patents are used to generalise the abstract functions of product core subsystems, where designers can obtain more comprehensive cross-domain technologies. This is conducive to breaking the design fixation of designers. Subject–Action–Object structural and functional similarity are combined to quickly extract cross-domain technologies in patents. Then multiple technical indicators are used to objectively evaluate and rank cross-domain technologies. This approach helps designers objectively select cross-domain technologies to change the way next-generation products work, enabling early planning of production conditions and a head start in the market. The method has been verified in a new product development project on peeling equipment, a new product that meets radical indicators is finally obtained.

Earthquake-triggered landslide interpretation model of high resolution remote sensing imageries based on bag of visual word

Traditional visual interpretation is often inefficient due to its excessively workload professional knowledge and strong subjectivity. Therefore, building an automatic interpretation model on high spatial resolution remote sensing images is the key to the quick and efficient interpretation of earthquake-triggered landslides. Aiming at addressing this problem, a landslide interpretation model of high-resolution images based on bag of visual word (BoVW) feature was proposed. The high-resolution images were pre-processed, and then BoVW feature and support vector machine (SVM) was adopted to establish an automatic landslide interpretation model. This model was further compared with the currently widely used Histogram of Oriented Gradient(HoG) feature extraction model. In order to test the effectiveness of the method, typical landslide images were selected to construct a landslide sample library, which was subsequently utilized as the foundation for conducting an experimental study. The results show that the accuracy of landslide extraction using this method reaches as high as 89%, indicating that the method can be used for the automatic interpretation of landslides in disaster-prone areas, and has high practical value for regional disaster prevention and damage reduction.

MORPHOLOGY AND PHONOSTYLISTICS OF IMITATIVE WORDS IN THE ENGLISH AND UZBEK LANGUAGES

The purpose of the study is to identify the typological features of imitative words in the English and Uzbek languages, as well as their semantic and contextual characteristics. The acceptance of imitative units as lexemes with independent meaning is characteristic of the English language, but morphologically, English onomatopoeias are not included in the group of imitatives, but in the series of interjections. They are not only an exclamatory sentence, but also function as a possessive, participial, attributive, complementary, or case in a compound or together with a verb. Imitative words in English are lexemes with independent meaning, which can take word-building affixes and act as different parts of speech. The imitative units in this language are mostly monosyllabic. In English, there are more words that imitate sound, and words that imitate state are included in the category of onomatopes. Onomatopoeia in English often has a figurative meaning as well as a literal meaning. In English linguistics, they are also called imitative units, that is, exclamations. English onomatopoeic units are also used figuratively to refer to other categories. Onomatopoeia, used in such a figurative sense, becomes an indirect imitatives. Sometimes the word imitative refers to a group of direct or indirect imitatives. Such onomatopoeia can serve as a phraseological unit expressing a mode of action used in a figurative sense.

Morphological and semantic features of the words of semantics state in modern English

Different approaches to determining the status of words of semantics state in modern linguistics are analyzed, the partial lexical potential of words of semantics state is outlined, the morphological and semantic features of words of semantics state in English are described, the attempt to divide words of semantics state into lexical-semantic groups is made in the article. It was noted that words of semantics state give a description of natural phenomena, physical and mental states of man, the core of words of semantics state in English is predicative adjectives in the predicate function. The basis of the study of words of semantics state in English is morphological features. The morphological characteristics of words of semantics state were singled out. It was found that morphologically words of semantics of the state are derived from adjectives, nouns and Participles II. Human perception is the basis in the division of words of semantics state into lexical and semantic groups. The growth of words of semantics state in English is due to the transition to them other parts of speech.

The effects of syntactic vs. semantic feature analysis of words on Iranian EFL learners' reading comprehension

IntroductionThe development of learners' semantic and syntactic knowledge of words and vocabulary plays an essential role in reading comprehension. This study attempted to investigate and compare the impact of instructing syntactic and semantic analyses of word features on Iranian EFL learners' reading comprehension.MethodsThree groups were selected: one was the control group and two were used as experimental groups. Students in all groups took part in a reading pretest. Two experimental groups received specific treatments, while the control group followed a traditional syllabus. All groups took part in a reading comprehension posttest at the end of the syllabus.Results and discussionThe results revealed that the syntactic analysis group outperformed the semantic analysis and control groups in the posttest. In addition, the participants in the semantic analysis group outperformed the students in the control group in the posttest. The results of this study could help teachers, learners, and textbook writers to improve reading skills in teaching, learning, and material development.

Understanding the adaptation difference of loanwords through COVID-19: a comparative analysis of Japanese and Korean

ABSTRACT As globalisation advances, an influx of loanwords has been seen in many languages in recent years. Japanese and Korean have similar grammatical features and many English-based loanwords. This study aims to clarify the difference in loanwords in Japanese and Korean adaptation, focusing on substituting alternative native lexicons through COVID-19. First, we collected COVID-19-related news articles in 2020 and extracted COVID-19-related loanwords in Japanese and Korean. Second, we examined the number of loanwords at an initial stage and investigated their changes compared to their alternative native lexicons. Three primary findings emerged from this study: (1) a similar number of loanwords were observed in Japanese and Korean, (2) the two languages had common features in that new words with different meanings or those that do not exist in English (pseudo-anglicisms) were devised based on the adapted loanwords, and (3) more loanwords were retained in Japanese, while relatively many loanwords in Korean became extinct or were replaced by loanwords’ alternative native lexicons with time. These findings indicate that substitution by alternative native lexicons leads to the lower usage of loanwords in Korean, even though the two languages adapted similar quantities of loanwords at the initial stage.

Near duplicate detection of images with area and proposed pixel‐based feature extraction

SummaryEfficient and accurate near‐duplicate recognition is the trendy research area. Identification of invalid near‐duplicate images offers a wide range of applications, including digital picture forensics, web‐scale retrieval, and, social media analysis. This article intends to introduce a novel near duplicate detection model of images that consists of two stages such as (i) feature extraction and (ii) similarity computation. Originally, the image database is subjected to extracting the features, in which the area‐based features and pixel‐based features are extracted. Here, the area‐based feature extraction includes the contrast context histogram (CCH‐descriptors) and improved weighted bag of visual word (w‐BovW) features; the pixel‐based feature extraction includes the texture features like the proposed local vector pattern. Once the query image is given as the input, it is subjected to the feature extraction stage. Then, the feature vector database and the extracted features of query images are evaluated under similarity computation via improved Jaccard similarity evaluation. Thus, the near duplicate detection of the image is obtained in an effective manner.

Emotional factors of early vocabulary in Spanish as a second language

AbstractPrevious studies analysing the differences in emotionality in first and second language suggest that affective content of lexical items is modulated in certain contexts. This paper investigates the differences in valence and arousal ratings for 300 early words, in both oral and written modalities, through speakers’ subjective appraisal of words given by two immersion groups of Spanish late bilinguals (Chinese and European) compared with a group of native speakers. The main goal of our study is to identify the lexical areas where variability occurs, regarding to a set of affective (emotional charge and intensity), grammatical (nouns, adjectives and verbs) and semantic (concreteness) features of words. Our results show that valence is the dimension where the greatest variability is observed between native and bilinguals, although the influence of the independent factors differs considerably. Besides, arousal yields illuminating data regarding the grammatical category of words and differentiation between the groups of participants.

Prosody of F. W. Haack’s dictionary

The article deals with the notation of prosodic features of Lithuanian words in F. W. Haack’s Lithuanian-German and German-Lithuanian dictionary (1730). First, the place of stress (in some cases also tone) is shown by Haack’s diacritical marks. Second, in some cases the place of stress is indirectly reflected by orthographic devices used to mark vowel quantity, e.g., the use of two different letters <i> and <y> for the long vowel y or the use of double consonants to mark the brevity of the preceding vowel. Finally, a separate valuable source of data for Lithuanian historical accentology is constituted by hand-written diacritical marks placed above some words in the copy of the dictionary held at Vilnius University Library.

Improved DeepFM Recommendation Algorithm Incorporating Deep Feature Extraction

In recent years, deep learning has been applied to the field of recommendation, which can learn complex user interaction features and make better recommendations. However, deep learning only focuses on the interaction of high-order features and neglects the low-order features. The DeepFM model combines the linear FM (Factorization Machines) model and the deep DNN (Deep Neural Network) model to realize the interactive learning of low-order and high-order features, but it does not take into account that user interests will change dynamically with time. When the data sparsity is high, it cannot be effectively recommended. Based on this, an improved DeepFM recommendation algorithm that combines depth feature extraction was proposed, named fDeepFM. Firstly, the word features are transformed into low-dimensional dense vectors through the Embedding layer. Then Doc2Vec is combined to mine item features with context, and the two are stitched together as the input to the FM model and DNN model. Subsequently, user features are input to the GRU (Gated Cyclic Unit) model according to different cycles to mine user features. Finally, the results of the FM model, DNN model, and GRU model are combined by linear stitching as the overall output of the fDeepFM model. Experiments were carried out on Movielens-20M and Amazon data sets. The experimental results showed that MAE, RMSE, F1-score, and AUC on the Movielens-20M data set were optimized by 1.69%, 2.4%, 1.67%, and 2.28%, respectively; On the Amazon dataset, MAE, RMSE, F1-score, and AUC are optimized by 3.2%, 3.86%, 1.63%, and 2.2% respectively compared with DeepFM.

“Thank you for the terrific party!” – An analysis of Hungarian negative emotive words

Abstract The term negative emotive word refers to those words that, on their own, i.e. without context, have a semantic content that may be associated with negative emotion, but sometimes they lose it partly or wholly. In the literature negative emotive words are mainly discussed within the group of intensifiers, e.g. awfully good. In the present paper, we call this phenomenon polarity loss. At the same time, there is another use of negative emotive words that is rarely discussed in the literature, namely the case where the examined word, despite its negative semantic content, expresses a positive evaluation of the speaker, e.g. brutális alaplap (lit. ‘brutal motherboard’ – ‘high quality motherboard’). We call this phenomenon polarity shift. The aim here is to thoroughly examine the two different phenomena on the basis of the data of a Hungarian speech corpus HuTongue. After an in-depth analysis of the qualitative and quantitative features of negative emotive words, we propose corresponding ways of their meaning representations, using a lexical pragmatic approach and the concept of enantiosemy.

Triplet Contrastive Learning for Aspect Level Sentiment Classification

The domain of Aspect Level Sentiment Classification, in which the sentiment toward a given aspect is analyzed, attracts much attention in NLP. Recently, the state-of-the-art Aspect Level Sentiment Classification methods are devised by using the Graph Convolutional Networks to deal with both the semantics and the syntax of the sentence. Generally, the parsing of syntactic structure inevitably incorporates irrelevant information toward the aspect. Besides, the syntactic and semantic alignment and uniformity that contribute to the sentiment delivery is currently neglected during processing. In this work, a Triplet Contrastive Learning Network is developed to coordinate the syntactic information and the semantic information. To start with, the aspect-oriented sub-tree is constructed to replace the syntactic adjacency matrix. Further, a sentence-level contrastive learning scheme is proposed to highlight the features of sentiment words. Based on The Triple Contrastive Learning, the syntactic information and the semantic information are thoroughly interacted and coordinated whilst the global semantics and syntax can be exploited. Extensive experiments are performed on three benchmark datasets and achieve accuracies (BERT-based) of 87.40, 82.80, 77.55 on Rest14, Lap14, and Twitter datasets, which demonstrate that our approach achieves state-of-the-art results in Aspect Level Sentiment Classification task.

Older Adults Show Intraindividual Variation in the Use of Predictive Processing

ABSTRACT Background The use of prediction can aid language comprehension through preactivation of relevant word features. However, predictions can be wrong, and it has been proposed that resolving the mismatch between the predicted and presented item requires cognitive resources. Older adults tend not to predict and instead rely more on passive comprehension. Here, we tested, using an intraindividual approach, whether older adults consistently use this less demanding processing strategy while reading or whether they attempt to predict on some trials. Methods We used a cross-task conflict paradigm. Younger and older participants self-paced to read sentences that ended with either an expected or unexpected word. Each sentence was then followed by a flanker stimulus that could be congruent or incongruent. We examined responses within and across the two tasks. Results Unexpected words were in general read as quickly as expected words, indicating that typical processing of these words was similar. However, for both younger and older adults, there was a greater proportion of very slow trials for unexpected words, revealing different processing on a subset of trials. Critically, in older adults, these slowly read unexpected words engaged control, as seen in speeded responses to incongruent flanker stimuli. Conclusion Using a cross-task conflict paradigm, we showed that older adults are able to predict and engage cognitive resources to cope with prediction violations, but do not opt to use these processes consistently.

Re-LSTM: A long short-term memory network text similarity algorithm based on weighted word embedding

Natural language processing text similarity calculation is a crucial and difficult problem that enables matching between various messages. This approach is the foundation of many applications. The word representation features and contextual relationships extracted by current text similarity computation methods are insufficient, and too many factors increase the computational complexity. Re-LSTM, a weighted word embedding long and short-term memory network, has therefore been proposed as a text similarity computing model. The two-gate mechanism of Re-LSTM neurons is built on the foundation of the conventional LSTM model and is intended to minimise the parameters and computation to some level. The hidden features and state information of the layer above each gate are considered for extracting more implicit features. By fully utilising the feature word and its domain association, the feature word’s position, and the word frequency information, the TF-IDF method and the χ²-C algorithm may effectively improve the representation of the weights on the words. The Attention mechanism is used in Re-LSTM to combine dependencies and feature word weights for deeper text semantic mining. The experimental results demonstrate that the Re-LSTM model outperforms baselines in terms of precision, recall, accuracy, and F1 values, all of which reach above 85% when applied to the QQPC and ATEC datasets.

A rule-based/BPSO approach to produce low-dimensional semantic basis vectors set

The present study aims to generate low-dimensional explicit distributional semantic vectors. In explicit semantic vectors, each dimension corresponds to a word, which makes word vectors interpretable. In this study, a new approach is proposed to obtain low-dimensional explicit semantic vectors. Firstly, the suggested approach considers three criteria, namely, word similarity, number of zeros, and word frequency as features for words in a corpus. Next, some rules are extracted to obtain the initial basis words using a decision tree which is drawn based on the three features. Secondly, a binary weighting method is proposed based on the binary particle swarm optimization algorithm which obtains NB = 1000 context words. In addition, a word selection method is used to provide NS = 1000 context words. Thirdly, the golden words of the corpus are extracted based on the binary weighting method. Subsequently, the extracted golden words are added to the context words which are selected by the word selection method as the golden context words. The ukWaC corpus is utilized for constructing the word vectors. MEN, RG-65, and SimLex-999 test sets are used to evaluate the word vectors. Next, the results are compared to a baseline which uses 5K most frequent words in the corpus as the context words. The baseline method uses a fixed window to count the cooccurrences. The word vectors are obtained using the 1000 selected context words along with the golden context words. Compared to the baseline method, the suggested approach can increase Spearman?s correlation coefficient for the MEN, RG-65, and SimLex-999 test sets by 4.66%, 14.73%, and 1.08%, respectively.

Literature Review on Application of Natural Language Processing and Machine Learning Techniques for Risk Prediction of Mucormycosis

Abstract: Mucormycosis is an infection caused by fungi capable of angio-invasion that is associated with high mortality and morbidity. Recently, An AI device was developed for detecting mucormycosis using Fourier Transform Infra-Red(FITR) sensors where human serum samples were tested using Fourier Transform Infra- Red Scanner. To obtain health outcome for various diseases, Clinical NLP has been extensively utilised. Word Embedding techniques and Feature Engineering Models in NLP convert clinical text data from EHR(Electronic Health Record) into useful format that serve as input for machine learning classification algorithms.

A Sociolinguistic Study on Korean Names of Immigrants in Korean Society

The purpose of this study is to find out factors that immigrants settling in Korean society decide their names and the social value of their names. In order to accomplish this, an online survey was conducted from August 1 to 5, 2022 to collect a total of 80 valid questionnaires, and a phone interview was conducted to complement its shortcomings. Results of the study are summarized as follows. First, as a result of examining the immigrants’ names by word types, they were found in the order of Chinese character words, loanwords, and mixed words. Second, the meanings immigrants wanted to include in their names was in the order of appearances, attitudes of life, ability and success, and luck and grace. Third, those who named the immigrants appeared in the order of parents, spouses, myself, or parents-in-law, acquaintances, relatives and grandparents. This study can be said to be of great significance in that it is possible to grasp one aspect of the language culture that immigrants are building in their lives by examining sociolinguistic characteristics of their names in Korean society.

Graph convolutional neural networks‐based assessment of students' collaboration ability

AbstractAs 21st‐century skills have become increasingly important, collaboration ability is now considered essential in many areas of life. Different theoretical frameworks and assessment tools have emerged to measure this skill. However, more applied studies on its implementation and assessment in current educational settings are required. This research accordingly uses Graph Convolutional Neural Networks (GCNs) to assess students' collaboration ability from students' assignments. The Pearson correlation coefficient is used to measure the similarity of the level of students' collaboration ability, and similar students are linked together to establish an adjacency matrix. By sorting through relevant literature and selecting the feature words that represent the strength of collaboration ability, calculating the similarity between the preprocessed student data and each selected feature word, after which the highest value of the similarity as the feature value of the student for this feature and establish the student feature matrix. Finally, the GCNs are jointly trained by the adjacency matrix and the feature matrix. The results show that this method can effectively assess students' collaboration ability. Moreover, compared with other text classification methods, the GCNs selected in this paper has higher accuracy.