Piece Of Text Research Articles

Denoising Graph Inference Network for Document-Level Relation Extraction

Relation Extraction (RE) is to obtain a predefined relation type of two entities mentioned in a piece of text, e.g., a sentence-level or a document-level text. Most existing studies suffer from the noise in the text, and necessary pruning is of great importance. The conventional sentence-level RE task addresses this issue by a denoising method using the shortest dependency path to build a long-range semantic dependency between entity pairs. However, this kind of denoising method is scarce in document-level RE. In this work, we explicitly model a denoised document-level graph based on linguistic knowledge to capture various long-range semantic dependencies among entities. We first formalize a Syntactic Dependency Tree forest (SDT-forest) by introducing the syntax and discourse dependency relation. Then, the Steiner tree algorithm extracts a mention-level denoised graph, Steiner Graph (SG), removing linguistically irrelevant words from the SDT-forest. We then devise a slide residual attention to highlight word-level evidence on text and SG. Finally, the classification is established on the SG to infer the relations of entity pairs. We conduct extensive experiments on three public datasets. The results evidence that our method is beneficial to establish long-range semantic dependency and can improve the classification performance with longer texts.

Performance Comparison of Transformer-Based Models on Twitter Health Mention Classification

Health mention classification classifies a given piece of text as a health mention or not. However, figurative usage of disease words makes the classification task challenging. To address this challenge, consideration of emojis and surrounding words of the disease names in the text can be helpful. Transformer-based methods are better at capturing the meaning of a word based on its surrounding words compared to traditional methods. However, there are numerous transformer-based methods available and pretrained on natural language processing (NLP) data that are inherently different from Twitter data. Moreover, the size of these models varies in terms of the number of parameters. Hence, it is challenging to decide and choose one of these methods for fine-tuning it on the downstream tasks such as tweet classification. In this work, we experiment with nine widely used transformer methods and compare their performance on the personal health mention classification of tweet data. Furthermore, we analyze the impact of model size on the classification task and provide a brief interpretation of the classification decision made by the best performing classifier. Experimental results show that RoBERTa outperforms all other models by achieving an F1 score of 93%, while two other models perform similarly by achieving an F1 score of 92.5%.

Text highlighting: Three methodological studies to inform guidelines for implementation

Text highlighting was recently introduced as a method for exploring consumer attitudes and perceptions. It consists of asking participants to read a piece of text on a digital device while using highlighting functions to indicate those parts of the text that they ‘like’/feel positive about, as well as those parts they ‘dislike’/feel negative about. As with any new method, methodological research helps to develop recommendations for best practice in use. In this regard, the present research addressed three research questions (RQs) in three studies with participants from New Zealand, United Kingdom, Singapore and Malaysia (ntotal = 5381). In a qualitative approach, Study 1 (RQ1) validated the notion that the text highlighting task is not expected to induce bias. Study 2 addressed RQ2 and explored whether the process of completing the text highlighting task influence consumers’ topic- and product-related responses? There was minimal evidence of this, meaning that text highlighting can reasonably be used together with other types of consumer responses without much the risk of biasing the latter. RQ3 (Study 3) investigated whether the type of highlighting task performed influence text selection. To date the method has been implemented as a dual approach (i.e., selecting both ‘like’ and ‘dislike’ aspects of the text), however, this could tentatively bias either or both responses compared to a single response task where participants select only ‘like’ highlights or only ‘dislike’ highlights. Study 3 found no effect for ‘like’ highlights when comparing dual- and single-response highlighting. However, for ‘dislike’ highlighting, significantly fewer words were selected in the dual-response approach (although the difference in frequency of selection was < 10%). The findings were established in case studies pertaining to kiwifruit and biodynamic agriculture but require confirmation in studies with different products, texts and participants.

Text characterization based on recurrence networks

Several complex systems are characterized by exhibiting intricate properties that occur at multiple scales. These multi-scale characterizations are used in various applications. In particular, texts can be characterized by a hierarchical structure, which can be approached by using multi-scale concepts and methods. Here, we adopt an extension of the multi-scale, mesoscopic approach – hereafter referred to as a recurrence network – to represent text narratives, in which only the recurrent relationships among tagged parts of speech (subject, verb and direct object) are considered to establish connections among sequential pieces of text. The characterization of the texts was then achieved by considering scale-dependent complementary methods: accessibility and symmetry. To evaluate the potential of these concepts, we approached the problem of distinguishing between meaningful and meaningless texts and different literary genres (namely, fiction and non-fiction). A set of 300 books was considered and compared by using the above approaches. The recurrence network characterization was able to discriminate to some extent between real and meaningless and between the two genres assessed. Thus, our results indicate that recurrence networks are able to capture subtleties in book plots, suggesting that a similar methodology can be used in related networked applications.

Единство и множественность космогонического процесса в поэме Эмпедокла

Among the ancient Greek philosophers Empedocles is the one who attempted to create a complete picture of the world, taking into account the knowledge of the thinkers who preceded him. It is an entire philosophical system that explores eternal and true principles and seeks to discover the causes of the being of all things and at the same time to explain their empirical becoming. It is a theory of the cosmic cycle, an eternal alternation in which the four elements that are the roots of all things--earth, air, water and fire--interact with the opposing forces of Love and Enmity, both in macrocosmic and microcosmic perspective. Empedocles does not give preference to any of the four elements, as had been done before him, but gives each of them their proper place. He introduces acting forces, by means of which he explains the reasons for the appearance and destruction of the world, and, moreover, in his views one can see the foundations of future conceptions of an impersonal law. Because of the fragmentary nature of the poem’s text, however, it is still not easy for us to grasp Empedocles’ thought consistently. Based on his own observations and taking into account the knowledge accumulated by previous generations of scholars, the author tries to offer his own reconstruction of the cosmogonic process presented in Empedocles’ poem. The reconstruction is carried out taking into account new fragments from the Strasbourg papyrus, thanks to which we have at our disposal a rather long and coherent piece of text, which makes a significant contribution to understanding the philosopher’s thought. The emphasis of the article is on the physical exposition of the poem with the application of philological methods and the subsequent interpretation of Empedocles’ verses. The physics of unity and multiplicity within the interaction of the forces of Love and Enmity and the four roots is reconstructed. The article also considers the didactic component of the poem, showing that Empedocles does not think of himself as separate from sensual nature, and that he and his disciple Pausanias are aware of their full involvement in the universal cosmogonic process.

Where (and When) Did the Authors of Joshua 10:1–39, 11:1–15 Live?

Abstract This article challenges a common scholarly view regarding Josh 10:1–39, 11:1–15. The first edition of these episodes is commonly attributed to Judean authors. I offer arguments in favor of a northern Israelite provenance of the first edition, assessing the extracts for which there is convincing evidence of such provenance. I also critically examine the arguments in favor of a Judean composition, rejecting some of them, reevaluating others, and determining pieces of text within 10:1–39, 11:1–15 for which there is in fact convincing evidence of Judean authorship. Much of the analysis is focused on the level of familiarity with different regions of Eretz-Israel exhibited in different parts of the text. In addition, any portion within these episodes for which the geographical setting of composition can be determined is placed along the time line of the episodes’ textual development. Whenever possible I suggest the approximate date of composition for a text and assess whether the extract under discussion belongs to a relatively early layer or to a late, redactional one. I conclude that the first edition of 10:1–39, 11:1–15 was composed in the northern kingdom of Israel before 722 BCE, and that this edition was later revised and expanded by Judean authors, probably in the seventh century BCE.

Ontology Learning Applications of Knowledge Base Construction for Microelectronic Systems Information

Knowledge base construction (KBC) using AI has been one of the key goals of this highly popular technology since its emergence, as it helps to comprehend everything, including relations, around us. The construction of knowledge bases can summarize a piece of text in a machine-processable and understandable way. This can prove to be valuable and assistive to knowledge engineers. In this paper, we present the application of natural language processing in the construction of knowledge bases. We demonstrate how a trained bidirectional long short-term memory or bi-LSTM neural network model can be used to construct knowledge bases in accordance with the exact ISO26262 definitions as defined in the GENIAL! Basic Ontology. We provide the system with an electronic text document from the microelectronics domain and the system attempts to create a knowledge base from the available information in textual format. This information is then expressed in the form of graphs when queried by the user. This method of information retrieval presents the user with a much more technical and comprehensive understanding of an expert piece of text. This is achieved by applying the process of named entity recognition (NER) for knowledge extraction. This paper provides a result report of the current status of our knowledge construction process and knowledge base content, as well as describes our challenges and experiences.

Neurofuzzy semantic similarity measurement

Automatically identifying the degree of semantic similarity between two small pieces of text has grown in importance recently. Its impact on various computer-related domains and recent breakthroughs in neural computation has increased the opportunities for better solutions to be developed. This work contributes a neurofuzzy approach for semantic textual similarity that uses neural networks and fuzzy logics. The idea is to combine the capabilities of the deep neural models for working with text with the ones from fuzzy logic for aggregating numerical data. The results of our experiments suggest that such an approach can accurately determine semantic similarity.

Men’s image projection through discourse analysis

Speech acts are utterances that serve a function in communication. These speech acts were used to describe men’s images who are members of a fraternity. Fraternities exist due to the ideology of gender polarization. Power is central to men’s identities and this power is displayed through language use. This study investigated how language is used by the members of a fraternity to identify and assess men’s image and social status. It used a qualitative design using discourse analysis. This was done through transcribing and deconstructing a conversation or piece of text. The participants of the study were the members of a community-based fraternity group composed of college students, with ages ranging from 19-26 years old. Among the 40 members, there were at least eight members who were consistently present in three contexts of conversations: meetings, bonding sessions, and social gatherings, and were selected as participants of this study. The collection of data was done through recordings of men’s conversations with their consent. The data analysis procedure began with the recording of the conversations which were transcribed according to Kiesling’s (2008) transcription conventions. The researcher identified features in the text, such as themes in the text, especially those that relate to men’s images. A tape recorder was used to capture the actual words spoken by the participants and the transcription of data. This study suggested that behavior in the form of speech acts consistently manifested itself as an attribute of personality traits and the words men use to weave the images of who they are or are not.

DuCL: Dual-stage contrastive learning framework for Chinese semantic textual matching

Chinese semantic textual matching is a fundamental yet challenging task in natural language processing (NLP). How to accurately capture the features in a single piece of text and the interactive features between pieces of text is the core problem of the task. Although pretrained language models (PLMs) and contrastive learning (CL) have been applied to address the problem to some extent, the existing works usually just utilize contrastive learning to finetune the PLMs on one single perspective, such as the sentence or pair level, which neglects to capture the semantic features from the other perspective, leading to inefficient learning and suboptimal performance. To tackle the problem, we propose a novel dual-stage contrastive learning framework (DuCL) for Chinese semantic textual matching. Specifically, DuCL consists of two stages sequentially, i.e., CL on the sentence level and CL on the pair level, each of which is responsible to finetune PLMs from the corresponding perspective. Besides, DuCL introduces a block-enhanced interaction module to integrate token-level and block-level interactive features to generate a semantic matching representation for two pieces of text. Extensive experimental results on two real-world public datasets demonstrate that our method can achieve better performance than the representative and state-of-the-art methods.

The small things of Global South: Exploring the use of social media through translingualism

In this paper, we present a research approach that sheds light on how netizens on social media perform and negotiate their multimodal and multisemiotic repertoires embedded within their social media languaging practices. This approach brings multimodal social semiotics into conversation with the normativity of translingualism to problematise the notion of languages as being ‘ordinary’ or ‘mundane’, and to illustrate how translingual netizens deploy their knowledge of the features of different language scripts, modalities and ‘small things’ (e.g., the use of emojis, replies, and comments) to increase and exploit their communicative capacity. In order to explore this claim, drawing upon digital ethnography approaches as our guiding methodology, the study investigates a YouTube post and responding comments from Global South settings. We illustrate that the subtext of their translingual practices is influenced by how they move beyond discourses and ideologies from the Global North. The analysis will consider the nature of communication in the aforementioned online communities from historical and contemporary perspectives, focusing on how our participants exploit local linguistic diversity as a resource and on how they extract a piece of text or discourse from its original context and bring it to a new context (i.e., online) and modify this material so that it fits into the new context. This article, therefore, contributes to the emerging body of work on the normativity of translingualism in communities around the world.

Research on Lovelorn Emotion Recognition Based on Ernie Tiny

Topics related to sentiment classification and emotion recognition are an important part of the Natural Language Processing research field and can be used to analyze users' sentiment tendencies towards brands, understand the public's attitudes and opinions on public opinion events, and detect users' mental health, among others. Past research has usually been based on positive and negative emotions or multi-categorized emotions such as happiness, anger and sadness, while there has been little research on the recognition of the specific emotion of lovelorn. This study aims to identify the lovelorn emotion in text, using deep learning pretrained model ERNIR Tiny to train a dataset consisting of 5008 pieces of Chinese lovelorn emotion text crawled from social media platform Weibo and 4998 pieces of ordinary text extracted from existing available dataset. And finally, it was proved that ERNIE Tiny performs well in classifying whether a text contains lovelorn emotion or not, with F1 score of 0.941929, precision score of 0.942300 and recall score of 0.941928 obtained on the test set.

A 1-Gram Sentiment Analysis Algorithm for Detecting Cyberbullying in Online Social Networks

Online social networking (OSN) sites in addition to providing business and recreational opportunities are fast becoming a breeding ground for cyberbullying activities. Cyberbullying is an act of harassing or insulting a person by sending messages that are hurting or threatening in nature using electronic communication. Such messages include threats, harassment, and humiliating messages to victims. Other forms are sexual harassments, sexual predating, etc. Cyberbullying poses threat to the physical and mental health of the victims. In this study, sentiments analysis was used to computationally recognize and categorize the opinions, views, and ideas expressed in a piece of text in social media to determine and establish whether the writer's attitude towards a particular topic, person, or a product is positive or negative. The study adopted both quantitative and qualitative approaches. Posts from Facebook were collected and analyzed. The software developed during the research was able detect the presence of cyberbullying in user contents. Results showed promising ability of the software to detect and suspend cyberbullying contents.

Comprehensive Readability Assessment of Scientific Learning Resources

Readability is the measure of how easier a piece of text is. Readability assessment plays a crucial role in facilitating content writers and proofreaders to receive guidance about how easy or difficult a piece of text is. In literature, classical readability, lexical measures, and deep learning based model have been proposed to assess the text readability. However, readability assessment using machine and deep learning is a data-intensive task, which requires a reasonable-sized dataset for accurate assessment. While several datasets, readability indices (RI) and assessment models have been proposed for military agencies manuals, health documents, and early educational materials, studies related to the readability assessment of computer science literature are limited. To address this gap, we have contributed Computer science (CS) literature dataset <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">AGREE</b> , comprising 42,850 learning resources(LR). We assessed the readability of learning objects(LOs) pertaining to domains of Computer Science (CS), machine learning (ML), software engineering (SE), and natural language processing (NLP). LOs consists of research papers, lecture notes and Wikipedia content of topics list of learning repositories for CS, NLP, SE and ML in English Language. From the statistically significant sample of LOs two annotators manually annotated LO’s text difficulty and established gold standard. Text readability was computed using 14 readability Indices (RI) and 12 lexical measures (LM). RI were ensembled, and readability measures were used to train the model for readability assessment. The results indicate that the extra tree classifier performs well on the AGREE dataset, exhibiting high accuracy, F1 score, and efficiency. We observed that there is no consensus among readability measures for shorter texts, but as the length of the text increases, the accuracy improves. The AGREE and SELRD datasets, along with the associated readability measures, provide a novel contribution to the field. They can be used to train deep learning models for readability assessment, develop recommender systems, and assist in curriculum planning within the domain of Computer Science. In the future, we plan to scale AGREE by adding more LOs and adding multimedia LOs. In addition, we would explore the use of deep learning methods for improved readability assessment.

Personalized Multi-document Text Summarization using Deep Learning Techniques

The summary of a large piece of text or a document is a concise description of the same thing. It must retain most of the important points from the document and remove any kind of verbosity. The text summarization task is an information processing scheme that given a document or a set of documents, mines the most essential content from the source by considering the user or task at hand and presents the summary in a well-formed and brief text. Summarization can be done not just on one document, it can be done on a set of documents as well, which is called multi-document summarization. The proposed approach considers and in-corporates user preferences for the summarization task. Depending on the current user or current task, the summary could differ essentially. For an instance, a summary on ‘photosynthesis’, would be very different for the kid in 4th Grade vs. a student doing a bachelor's in Science. Therefore, while writing a summary, the reading history of the user is employed as a source of personalizing text summarization tasks. The proposed method is experimentally evaluated in the domain of news articles and obtained better summaries capable of extracting important concepts based on user preferences explained in the document when considering the relevant domain terms in the process of multi-document text summarization.

Sentiment Analysis using Bidirectional LSTM Network

Sentiment analysis is a cognitive tool to extract the emotional tone of a piece of text. It is an area of research that is actively pursued in Natural Language Processing. Social media, forums and blogs, among other places, have seen a massive surge in the number of personalized reviews since the emergence of Internet-based applications. Sentiment analysis is primarily concerned with the classification and prediction of users' thoughts and emotions from these reviews. In recent years, numerous deep learning techniques have emerged to achieve this task. This paper provides a technical summary of Sentiment Analysis using a Bidirectional LSTM network. This model is capable of handling long-term dependencies by introducing memory into the model for making better predictions. The Amazon Product Review dataset served as the source of data for this research. Concretely, the analysis is performed on 104,975 product reviews reflecting users' attitudes toward mobile electronics products. The proposed model attempts to classify the reviews into two categories: positive and negative. Finally, the paper outlines the results of the analysis and suggests potential avenues for future research.

Heterogeneous Feature Alignment and Fusion in Cross-Modal Augmented Space for Composed Image Retrieval

Composed image retrieval (CIR) aims at fusing a reference image and text feedback to search for the desired images. Compared to general image retrieval, it can model the users' search intent more comprehensively and search the target images more accurately, which has significant impacts in various real-world applications, such as E-commerce and Internet search. However, because of the existing heterogeneous semantic gap, the synthetic understanding and fusion of both image and text are difficult to implement. In this work, to tackle this difficult problem, we propose an end-to-end framework MCR, which uses text and images as retrieval queries. The framework mainly includes four pivotal modules. Specifically, we introduce the Relative Caption-aware Consistency (RCC) constraint to align text pieces and images in the database, which can effectually bridge the heterogeneous gap. The Multi-modal Complementary Fusion (MCF) and Cross-modal Guided Pooling (CGP) are constructed to mine multiple interactions between image local features and text word features and learn the complementary representation of the composed query. Furthermore, we develop a plug-and-play Weak-text Semantic Augment (WSA) module for datasets with short or incomplete query texts, which can supplement the weak-text features and is conducive to modeling an augmented semantic space. Extensive experiments demonstrate the practical superior performance over the existing state-of-the-art empirical algorithms on several benchmarks.

GPTZero Performance in Identifying Artificial Intelligence-Generated Medical Texts: A Preliminary Study.

With emergence of chatbots to help authors with scientific writings, editors should have tools to identify artificial intelligence-generated texts. GPTZero is among the first websites that has sought media attention claiming to differentiate machine-generated from human-written texts. Using 20 text pieces generated by ChatGPT in response to arbitrary questions on various topics in medicine and 30 pieces chosen from previously published medical articles, the performance of GPTZero was assessed. GPTZero had a sensitivity of 0.65 (95% confidence interval, 0.41-0.85); specificity, 0.90 (0.73-0.98); accuracy, 0.80 (0.66-0.90); and positive and negative likelihood ratios, 6.5 (2.1-19.9) and 0.4 (0.2-0.7), respectively. GPTZero has a low false-positive (classifying a human-written text as machine-generated) and a high false-negative rate (classifying a machine-generated text as human-written).

Feature-Based Opinion Classification Using the KPCA Technique: Concept and Performance Evaluation

Over the last several years, a widespread trend on the internet has been the proliferation of online evaluations written by people with whom they share their ideas, interests, experiences, and opinions. Opinion mining, also known as sentiment analysis, is the process of classifying pieces of text written in a natural language on a subject into positive, negative, or neutral categories according to the human emotions, views, and feelings that are communicated in that text. The field of sentiment analysis has progressed to the point that it can now analyse internet evaluations and provide significant information to people as well as corporations, which may assist these parties in the decision-making process. In the proposed model, feature extraction extracts the collection of features that are both semantically and statistically significant using the kernel principal component analysis (KPCA) method. According to the findings of the simulations, the suggested model performs better than other existing models.

Rwanga Movement and Cultural Critical Speech

Cultural Criticism in Literature was of a reaction toward Structuralism and Semiology, which would see literature as a linguistic phenomenon.&nbsp; In other words, literature used to be an artistic, esthetic and poetic phenomenon. But, cultural criticism emerges and releases literature from that framework and becomes a new method for studying that cultural structure which has created that literature, simultaneously, studying literature from its cultural, social, historical and political context. In our viewpoint, Rwanga Movement was more of a cultural phenomenon than a literary one such as a piece of text. This research (Rwanga Movement and Cultural Critical Speech) consists of two chapters. The first chapter is a literary chapter containing three sections. The first section discusses terminology related to cultural criticism. The second section is dedicated to cultural criticism which replaces literary criticism, and how wider the area cultural criticism works in than that of literary criticism. The third section discusses the cultural speech of Rwanga Movement for which we have worked on the Movement’s manifest. The second chapter is a applied work containing two parts. The first part discusses the role of Rwanga movement on how it works on the structure of the making of literary text. The second part discusses the aging of Kurdish literature and the role of Rwanga movement in its revival as a cultural phenomenon. The result of our research is discussed in some points. The Harvard system has been used for the list of the references.