Features Of Sentences Research Articles

Research on Chinese Text Feature Extraction and Sentiment Analysis Based on Combination Network

The complexity of Chinese language system brings great challenge to sentiment analysis. Traditional artificial feature selection is easy to cause the problem of inaccurate segmentation semantics. High quality preprocessing results are of great significance to the subsequent network model learning. In order to effectively extract key features of sentences, retain feature words while removing irrelevant noise and reducing vector dimensions, an algorithm module based on sentiment lexicon combined with Word2vec incremental training is proposed in terms of feature engineering. Firstly, the data set is cleaned, and the sentence is segmented by loading a custom sentiment lexicon with Jieba. Secondly, the results after stopping words are obtained through Skip-gram training algorithm to obtain the word vector model. Secondly, the model is added to a large corpus for incremental training to obtain a more accurate word vector model. Finally, the features are learned and classified by inputting the embedding layer into the neural network model. Through the comparison experiment of multiple models, it is found that the combined model (CNN-BiLSTM-Attention) has better classification effect and better application ability.

Coarse and Fine Granularity Graph Reasoning for Interpretable Multi-Hop Question Answering

Interpretable multi-hop question answering requires step-by-step reasoning over multiple documents and finding scattered supporting facts to answer the question. Prior works have proposed the entity graph method to aggregate the entity information to improve the ability of reasoning. However, the entity graph loses some non-entity information that is also important to understand the semantics. Moreover, the entities distributed in the noisy sentences may mislead the reasoning process. In this paper, we propose the Coarse and Fine Granularity Graph Network (CFGGN), a novel interpretable model that combines both sentence information and entity information to answer the multi-hop questions. The CFGGN consists of a coarse-grain module to perform sentence-level reasoning and a fine-grain module to make entity-level reference. In sentence-level reasoning, the sentence graph is constructed to filter out the noisy sentences and capture the sentence features. In entity-level reference, a dynamic entity graph is used for the entity-level reasoning. We design a fusion module to integrate information of different granularity. To enhance the interpretability of the overall process, we calculate the reasoning score for each step and present the reasoning path from the multiple documents to the final answer. Evaluation on the HotpotQA dataset in the distractor setting shows that our method outperforms the published SOTA entity-based method in five out of six metrics.

Masked Sentence Model Based on BERT for Move Recognition in Medical Scientific Abstracts

Abstract Purpose Move recognition in scientific abstracts is an NLP task of classifying sentences of the abstracts into different types of language units. To improve the performance of move recognition in scientific abstracts, a novel model of move recognition is proposed that outperforms the BERT-based method. Design/methodology/approach Prevalent models based on BERT for sentence classification often classify sentences without considering the context of the sentences. In this paper, inspired by the BERT masked language model (MLM), we propose a novel model called the masked sentence model that integrates the content and contextual information of the sentences in move recognition. Experiments are conducted on the benchmark dataset PubMed 20K RCT in three steps. Then, we compare our model with HSLN-RNN, BERT-based and SciBERT using the same dataset. Findings Compared with the BERT-based and SciBERT models, the F1 score of our model outperforms them by 4.96% and 4.34%, respectively, which shows the feasibility and effectiveness of the novel model and the result of our model comes closest to the state-of-the-art results of HSLN-RNN at present. Research limitations The sequential features of move labels are not considered, which might be one of the reasons why HSLN-RNN has better performance. Our model is restricted to dealing with biomedical English literature because we use a dataset from PubMed, which is a typical biomedical database, to fine-tune our model. Practical implications The proposed model is better and simpler in identifying move structures in scientific abstracts and is worthy of text classification experiments for capturing contextual features of sentences. Originality/value T he study proposes a masked sentence model based on BERT that considers the contextual features of the sentences in abstracts in a new way. The performance of this classification model is significantly improved by rebuilding the input layer without changing the structure of neural networks.

THE TYPOLOGICAL DOMINANT – BACKGROUND OF SYSTEMATIZATION OF SYNTACTICALLY NON-SEGMENTED SENTENCES IN UKRAINIAN LINGUISTICS

Paper deals with the structural and semantic types of syntactically non-segmented constructions. The topicality of the study is due to the need to systematize all structural and semantic types of syntactically non-segmented sentences of the Modern Ukrainian language and the absence of special works on typological research of these units. The aim of this study is to determine the characteristics of the typological dominant – structural and semantic – in the two-dimensional typology of syntactically non-segmented sentences. The structural and semantic typological dominants are characterized. The article gives a detailed analysis of criteria for the allocation of structural and semantic types of unphraseological and phraseological non-segmented sentences. In unphraseological non-segmented sentences structural types are classified according to the partial expression of their structural components. The structural features of phraseological non-segmented sentences are the morphological nature of the constant and variable components, the position of the constant component.The semantic type is a model that is selected based on the type of categorical relation or the type of semantic-syntactic relation, combining various semantic varieties into a single semantic typology of syntactically non-segmented sentences.

Multifeature Interactive Fusion Model for Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis technology. In recent years, neural networks are widely used to extract features of aspects and contexts and proven to have a dramatic improvement in retrieving the sentiment feature from comments. However, due to the increasing complexity of comment information, only considering sentence or word features, respectively, may cause the loss of key text information. Besides, characters have more microscopic features, so the fusion of features between three different levels, such as sentences, words, and characters, should be taken into consideration for exploring their internal relationship among different granularities. According to the above analysis, we propose a multifeature interactive fusion model for aspect-based sentiment analysis. Firstly, the text is divided into two parts: contexts and aspects; then word embedding and character embedding are associated to further explore the potential features. Secondly, to establish a close relationship between contexts and aspects, features fusion of both aspects and contexts are exploited in our model. Moreover, we apply the attention mechanism to calculate fusion weight of features, so that the key features information plays a more significant role in the sentiment analysis. Finally, we experimented on the three datasets of SemEval2014. The results of experiment showed that our model has a better performance compared with the baseline models.

A Novel Neural Network-Based Method for Medical Text Classification

Medical text categorization is a specific area of text categorization. Classification for medical texts is considered a special case of text classification. Medical text includes medical records and medical literature, both of which are important clinical information resources. However, medical text contains complex medical vocabularies, medical measures, which has problems with high-dimensionality and data sparsity, so text classification in the medical domain is more challenging than those in other general domains. In order to solve these problems, this paper proposes a unified neural network method. In the sentence representation, the convolutional layer extracts features from the sentence and a bidirectional gated recurrent unit (BIGRU) is used to access both the preceding and succeeding sentence features. An attention mechanism is employed to obtain the sentence representation with the important word weights. In the document representation, the method uses the BIGRU to encode the sentences, which is obtained in sentence representation and then decode it through the attention mechanism to get the document representation with important sentence weights. Finally, a category of medical text is obtained through a classifier. Experimental verifications are conducted on four medical text datasets, including two medical record datasets and two medical literature datasets. The results clearly show that our method is effective.

Regression model focused on query for multi documents summarization based on significance of the sentence position

Document summarization is needed to get the information effectively and efficiently. One method used to obtain the document summarization by applying machine learning techniques. This paper proposes the application of regression models to query-focused multi-document summarization based on the significance of the sentence position. The method used is the Support Vector Regression (SVR) which estimates the weight of the sentence on a set of documents to be made as a summary based on sentence feature which has been defined previously. A series of evaluations performed on a data set of DUC 2005. From the test results obtained summary which has an average precision and recall values of 0.0580 and 0.0590 for measurements using ROUGE-2, ROUGE 0.0997 and 0.1019 for measurements using the proposed regression-SU4. Model can perform measurements of the significance of the position of the sentence in the document well.

Long story short: finding health advice with informative summaries on health social media

Purpose Whether automatically generated summaries of health social media can aid users in managing their diseases appropriately is an important question. The purpose of this paper is to introduce a novel text summarization approach for acquiring the most informative summaries from online patient posts accurately and effectively. Design/methodology/approach The data set regarding diabetes and HIV posts was, respectively, collected from two online disease forums. The proposed summarizer is based on the graph-based method to generate summaries by considering social network features, text sentiment and sentence features. Representative health-related summaries were identified and summarization performance as well as user judgments were analyzed. Findings The findings show that awarding sentences without using all the incorporating features decreases summarization performance compared with the classic summarization method and comparison approaches. The proposed summarizer significantly outperformed the comparison baseline. Originality/value This study contributes to the literature on health knowledge management by analyzing patients’ experiences and opinions through the health summarization model. The research additionally develops a new mindset to design abstractive summarization weighting schemes from the health user-generated content.

SENTENCE FEATURE IN STUDENTS’ ACADEMIC WRITING (Case Study in Polytechnic of Tonggak Equator Pontianak)

Abstract: Academic writing is one type of writing that should be mastered by students in Polytechnic of Tonggak Equator Pontianak. Academic writing is very important because it functions as a way to express an idea or another way of communication in doing research. Academic writing is essential to process in writing academic articles. Moreover, writing skills are an important part of communication. Academic writing is a specific ability of communication to put writers’ ideas on paper, to organize their knowledge, and then how to make sentences become a paragraph. This research is descriptive qualitative research. The writer collected the data by giving instructions to the students to write an academic article. The respondents are 60 students who are the representative of the students from class A to F in semester 5. This semester is chosen because they have academic writing subject. The result of the research shows that the most crucial problem in writing a sentence in academic context by students of Polytechnic Tonggak Equator Pontianak is in the sentence category. In this problem, students are not able to vary their sentences in their paragraphs that might cause the quality of their sentence is not proficient.Keyword: Sentence Feature, Academic Writing, Politeknik Tonggak Equator Students

A convolutional neural network-based linguistic steganalysis for synonym substitution steganography.

In this paper, a linguistic steganalysis method based on two-level cascaded convolutional neural networks (CNNs) is proposed to improve the system's ability to detect stego texts, which are generated via synonym substitutions. The first-level network, sentence-level CNN, consists of one convolutional layer with multiple convolutional kernels in different window sizes, one pooling layer to deal with variable sentence lengths, and one fully connected layer with dropout as well as a softmax output, such that two final steganographic features are obtained for each sentence. The unmodified and modified sentences, along with their words, are represented in the form of pre-trained dense word embeddings, which serve as the input of the network. Sentence-level CNN provides the representation of a sentence, and can thus be utilized to predict whether a sentence is unmodified or has been modified by synonym substitutions. In the second level, a text-level CNN exploits the predicted representations of sentences obtained from the sentence-level CNN to determine whether the detected text is a stego text or cover text. Experimental results indicate that the proposed sentence-level CNN can effectively extract sentence features for sentence-level steganalysis tasks and reaches an average accuracy of 82.245%. Moreover, the proposed steganalysis method achieves greatly improved detection performance when distinguishing stego texts from cover texts.

Sentiment Analysis using Feature Based Support Vector Machine – A Proposed Method

Business decisions for any service or product depend on sentiments by the people. The mood of people towards any event, service and product are expressed in sentiments. The text sentiment contains different linguistic features of sentence. A sentiment sentence also contains other features which are playing a vital role in deciding the polarity of sentiments.The features like duplication of sentiment, unknown emotics may change the polarity of sentiment.If features selection is proper one can extract better sentiments for decision making. A directed preprocessing will feed filtered input to any machine learning approach. Support vector machine proved as a good tool of machine learning for better sentiment analysis.Better use of parts os speech (POS) folled by guided preprocessing and evaluation will provide less errorus polarity of sentiments

Knowledge-oriented Hierarchical Neural Network for Sentiment Classification

Sentiment classification aims to classify the sentimental polarities of given texts. Lexicon-based approaches utilize lexical resources to explore the opinions according to some specific rules, whose effectiveness strongly depends on the goodness of the lexical resources and the rules. Traditional machine-learning methods tightly rely on feature engineering and external NLP toolkits with unavoidable errors. Deep learning models strongly rely on a large amount of labelled data to train their numerous parameters, which often suffer from overfitting issue since it is difficult to obtain sufficient training data. To address the issues, we design a model that combines Knowledge-oriented Convolutional Neural Network (K-CNN) and bidirectional Gated Recurrent Neural Network (biGRU) in a hierarchical way for sentiment classification. Firstly K-CNN is used to capture the n-gram features in sentences. Sentiment word filters are constructed in the knowledge-oriented channel of K-CNN based on the linguistic knowledge from SentiWv ordNet, which can capture the sentiment lexicons and alleviate overfitting effectively. Then biGRU with attention mechanism is utilized to model the sequential relations between sentences and obtain the document-level representation based on the relevance of each sentence to the final sentiment classification. Experiments on two datasets show that our model outperforms other classical deep neural network models.

Intonational pitch features of interrogatives and declaratives in Chengdu dialect

As a representative of southwestern Mandarin, the Chengdu dialect has its own distinctive pitch features in phonology of tone and intonation. Research on the pronunciation and lexical tone of the Chengdu dialect has a long history with a certain amount of theoretical results. However, research on intonation of Chengdu dialect is still rare. The writer provides an acoustic analysis of research into intonational pitch features of interrogative and declarative sentences of Chengdu dialect, discussing the F0 contour at the final syllable (character) of each sentence to find out if the statement or question mood is carried by the edge tone as well as the pitch perturbation between lexical tone and intonation on it. The results of this acoustic analysis show that there exist statement and question mood of Chengdu dialect carried by the final syllable within an intonational phrase as well as the perturbation on the final syllable (character) by the coexistence of its lexical tone and intonation.

Incorporating word attention with convolutional neural networks for abstractive summarization

Neural sequence-to-sequence (seq2seq) models have been widely used in abstractive summarization tasks. One of the challenges of this task is redundant contents in the input document often confuses the models and leads to poor performance. An efficient way to solve this problem is to select salient information from the input document. In this paper, we propose an approach that incorporates word attention with multilayer convolutional neural networks (CNNs) to extend a standard seq2seq model for abstractive summarization. First, by concentrating on a subset of source words during encoding an input sentence, word attention is able to extract informative keywords in the input, which gives us the ability to interpret generated summaries. Second, these keywords are further distilled by multilayer CNNs to capture the coarse-grained contextual features of the input sentence. Thus, the combined word attention and multilayer CNNs modules provide a better-learned representation of the input document, which helps the model generate interpretable, coherent and informative summaries in an abstractive summarization task. We evaluate the effectiveness of our model on the English Gigaword, DUC2004 and Chinese summarization dataset LCSTS. Experimental results show the effectiveness of our approach.

RENDERING FUNCTION FEATURES OF THE FRENCH COLLOQUIAL INTERROGATIVE CONSTRUCTIONS IN UKRAINIAN FICTION TRANSLATION

The article deals with the problems of colloquial interrogative sentences having the function features in the source and target fiction texts. The importance of the research of interrogative sentences is defined by frequent use of questioning in the process of communication and a close connection of the problem of questioning with other sociolinguistic issues. The given paper outlines function features of the colloquial interrogative sentences on the material of J.-M. Guenassia’s “The Incorrigible Optimists Club” and its Ukrainian translation by means of the analysis of possible ways of their rendering into Ukrainian. The author takes into account many works devoted to the study of questioning as a linguistic and translation category, paying special attention to the place of interrogative sentences in the French colloquial speech. The analysis of the colloquial interrogatives functioning in J.-M. Guenassia’s novel “The Incorrigible Optimists Club” allows the author to conclude that translation difficulties are caused not so much by their text-functional features, but rather by their structural, semantic, figurative, and socio-functional characteristics, as well as by the asymmetry of the structural elements and register polyphony of the source and target languages.

Deep learning model for unstructured knowledge classification using structural features

Automatic text classification is widely used as the basic method for analyzing data. While classification methods like the support vector machine (SVM) have exhibited impressive performance in the area, the recent use of deep learning has led to considerable progress in text classification. This study proposes a deep learning–based classification model called DEEP-I to classify information on national research and development with complex structural features, a large amount of text, and large-scale classes. In addition to the word–sentence structure of a simple document, the number of stacking layers of the deep model is increased in light of the higher-level structure of the items. Experiments on 180,000 datasets and 366 classification schemes showed that the proposed model can improve classification performance by 22.7% over the traditional SVM and 15.7% over a deep learning model that uses only structured features of word sentences. This improvement was achieved because the multi-layered stacking method was applied to enhance learning by increasing depth by five to 10 times that of the conventional deep learning model and effectively combining features of heterogeneous items. The proposed model is also applicable to datasets containing documents with complex structures.

Extractive summarization using supervised and unsupervised learning

In this paper, three methods of extracting single document summary by combining supervised learning with unsupervised learning are proposed. The purpose of these three methods is to measure the importance of sentences by combining the statistical features of sentences and the relationship between sentences at the same time. The first method uses supervised model and graph model to score sentences separately, and then linear combination of scores is used as the final score of sentences. In the second method, the graph model is used as an independent feature of the supervised model to evaluate the importance of sentences. The third method is to score the importance of sentences by supervised model, then as a priori value of nodes in the graph model, and finally use biased graph model to score sentences. On the data sets of DUC2001 and DUC2002, the ROUGE method is used as the evaluation criterion, which shows that the three methods have achieved good results, and are superior to the methods of extracting summary only using supervised learning or unsupervised learning. We also validate that priori knowledge can improve the accuracy of key sentence selection in graph model.

Indonesian Vocabulary Mastery of Early-aged Children in Paud Melati Makassar

Early-aged children are individuals from 0 to 6 year old with unique characteristics and in the stage of growth and development, both physical and mental. Several aspects developed for their education include moral and religious values, social, emotional feelings, autonomy, language, cognitive, physical/motor skill, and art (Ramli, 2005, p.50). The development of these aspects affect each other, that is why it has to be optimally developed in every activity. One aspect of those basic skills should be developed in early-aged children is language. The objectives of this research are to describe (1) the quantity of Indonesian vocabularies in early-aged children; (2) certain Indonesian word classes in early-aged children; (3) certain scopes of Indonesian vocabularies in early-aged children; (4) Indonesian basic sentence pattern in early-aged children; (5) Indonesian basic sentence features considered by the form of integrative phrases; (6) Indonesian basic sentence features considered by the number of integrative phrases. The results of the research show that the vocabulary quantity of early-aged children varies due to external and internal factors. It triggers their inputs to vary from one to another. Word classes mastered by them include noun, verb, adjective, adverb, numeral, pronoun, and preposition. Based on the findings in the field, they have also mastered several vocabulary scopes, such as kinship, activity, place, number, color, universal objects, and animal types. In line with that, sentence patterns that have been mastered by them are FN-FV, FN1-FN2, FN-FA, FN-Num, and FN–FP.

ФУНКЦІЙНИЙ ПОТЕНЦІАЛ ІМПЕРАТИВА У ВИСЛОВЛЕННЯХ РЕЛІГІЙНОЇ СЕМАНТИКИ (на матеріалі творів Г. Ф. Квітки-Основ'яненка)

The proposed article deals with the issue of the specific language of religious semantics as unique products of the thinking and speech activity of Ukrainians in view of the nature of their spiritual worldview. The relevance of the study is caused by necessity to follow up the realization of the peculiarities of Ukrainian’s appeals to God. The main task of the article is the analysis of the actual material, collected by the method of a complete sample from the works of H. F. Kvitka-Osnovianenko. The purpose of the proposed study is to reveal the specifics of the linguistic design of appeals of Ukrainians to God. It is indicated on the specifies the structural features of sentences that can express appeal to God, their functional-semantic peculiarity. An attempt to determine the functionality of the predicate-imperative as a center-forming element, including the transformed phraseologized sentences-interjections, was made. The examples of man’s conversion to God are statements presented in the form of imperative sentences with a clearly defined constituent in the form of an imperative (at the grammatical level). The imperative is quite suitable for the expression of various functional-semantic types of appeal to God. The vocative together with the predicate-imperative are the semantic-grammatical center of imperative religious sentences-statements. The ability of the imperative-vocative combination to transform into exclamatory sentence-phraseological units allows us to ascertain the functional potential of imperatives in the statements of religious semantics. Key words: imperative, imperative sentence, religious semantics, exclamatory sentences, communicators.

COMPOUND SENTENCES OF PURPOSE AND CAUSE AS A KIND OF POLYMEMBER STRUCTURES WITH THE DIRECT CAUSATIVE MEANING: STRUCTURAL AND SEMANTIC ASPEKT (on the material of the novels of Vasyl Skliar “Chornyi Voron”, “Marusia”)

Topicality of the research is due to the scientific need to systematize the reasons of syntactic structures in the studies which influence the choice of the writer. On this basis, the need of clarifying the factors that influenced the choice of writers is updated. This means that researchers pay attention not only to structural, semantic and communicative features of complex sentences, but special attention is paid to the study of their writing potential. Of course, expressive features and functions of complex sentences that are directly involved in their formulation and design composition are shown in fiction. In the contextual environment we are able to explore more features of such syntactic structures. Among the constructions that were not the subject of this comprehensive analysis, there are complex sentences with subordinate goals and causes as a variety of sentences dismembered with a value of condition in the novels by Vasyl Shklyar "Black Raven", "Marusya". The object of our scientific research is complex sentences with subordinate goals and causes as a variety of segmented structure sentences with the value of condition in the novels by Vasyl Shklyar "Black Raven", "Marusya". 
 The material of study includes novels by Vasyl Shklyar "Black Raven", in which "Marusya" 71 complex sentences of purpose, (33%), and 27 sentences of contractors reasons, (26%) of all complex sentences segmented structure with the value of condition. Were these singled out sentence structures perform a variety of functions: they help express the author’s attitude to the depicted events, reveal the inner world of the hero, a true atmosphere of sincere conversation. Complex sentences with subordinate causes in the analyzed Vasyl Shklyar novels are also represented, though not distinguished by the diversity of communication. They dominate in the stories of the characters, monologues and dialogues, landscape descriptions. These designs clearly differentiate artistic speech, eliminate ambiguity of complexity. Their functioning, semantic and stylistic role is regulated by individual author's style. Most sentences contain emotional and evaluative component, help to outline the spiritual ideals of the writer, his inner world and feelings. Certified units demonstrate the wealth of author’s artistic language. In this work we described only two types of sentences. Similar scientific research may be subject to further detailed studies and scientific interests.