Features Of Natural Language Research Articles

Implementation of Automatic Mesh Rules Generation by Word Features Relationship (AMRG-WFR) for Word Sense Disambiguation for Marathi Language

One common feature of natural languages is a single word having the different meanings. Detecting the correct sense of the word in the given context is known as word sense disambiguation. In Natural language processing WSD is always a challenging and difficult task. The accuracy of many systems like information retrieval, machine translation text summarization depends upon the module used to identify the correct sense of the word. In this paper we proposed an automatic mesh rule generation technique by word feature relationship for the task of word sense disambiguation for Marathi language. Marathi is one the most popular and morphologically rich language in India. We conducted all the experiments on the benchmark WordNet dataset developed at Indian Institute of Technology Bombay (IIT Bombay). The proposed algorithm contains three sections.In the first section supervised learning technique is used to create training data set. Mesh rules of object were created in second section and in last section the correct sense of ambiguous word matched with the given context. Results show that the proposed method has superior performance as compared with already developed approaches.

WND-Identifier: Automated and Efficient Identification of Wireless Network Devices

The widespread application of wireless communication technology brings great convenience to people, but security and privacy problems also arise. To assess and guarantee the security of wireless networks and user devices, discovering and identifying wireless devices become a foremost task. Currently, effective device identification is still a challenging issue, as device fingerprinting requires huge training datasets and is difficult to expand, and rule-based identification is not accurate and reliable enough. In this paper, we propose WND-Identifier, a universal and extensible framework for the identification of wireless devices, which can generate high-precision device labels (vendor, type, and product model) efficiently without user interaction. We first introduce the concept of device-info-related network protocols. WND-Identifier makes full use of the natural language features in such protocol messages and combines with the device description in the welcome page, thereby utilizing extraction rules to generate concrete device labels. Considering that the device information in the protocol messages may be incomplete or forged, we further take advantage of the application logic independence and stability of the device-info-related protocol, so as to build a multiprotocol text classification model, which maps the device to a known label. We conduct experiments in homes and public networks and present three application scenarios to verify the effectiveness of WND-Identifier.

Grammatical categories determination for Turkish and Kazakh languages based on machine learning algorithms and fulfilling dictionaries of link grammar parser

This research is aimed at identifying the parts of speech for the Kazakh and Turkish languages in an information retrieval system. The proposed algorithms are based on machine learning techniques. In this paper, we consider the binary classification of words according to parts of speech. We decided to take the most popular machine learning algorithms. In this paper, the following approaches and well-known machine learning algorithms are studied and considered. We defined 7 dictionaries and tagged 135 million words in Kazakh and 9 dictionaries and 50 million words in the Turkish language. The main problem considered in the paper is to create algorithms for the execution of dictionaries of the so-called Link Grammar Parser (LGP) system, in particular for the Kazakh and Turkish languages, using machine learning techniques. The focus of the research is on the review and comparison of machine learning algorithms and methods that have accomplished results on various natural language processing tasks such as grammatical categories determination. For the operation of the LGP system, a dictionary is created in which a connector for each word is indicated – the type of connection that can be created using this word. The authors considered methods of filling in LGP dictionaries using machine learning. The complexities of natural language processing, however, do not exclude the possibility of identifying narrower tasks that can already be solved algorithmically: for example, determining parts of speech or splitting texts into logical groups. However, some features of natural languages significantly reduce the effectiveness of these solutions. Thus, taking into account all word forms for each word in the Kazakh and Turkish languages increases the complexity of text processing by an order of magnitude

Forecasting the Suitability of Online Mental Health Information for Effective Self-Care Developing Machine Learning Classifiers Using Natural Language Features.

Background: Online mental health information represents important resources for people living with mental health issues. Suitability of mental health information for effective self-care remains understudied, despite the increasing needs for more actionable mental health resources, especially among young people. Objective: We aimed to develop Bayesian machine learning classifiers as data-based decision aids for the assessment of the actionability of credible mental health information for people with mental health issues and diseases. Methods: We collected and classified creditable online health information on mental health issues into generic mental health (GEN) information and patient-specific (PAS) mental health information. GEN and PAS were both patient-oriented health resources developed by health authorities of mental health and public health promotion. GENs were non-classified online health information without indication of targeted readerships; PASs were developed purposefully for specific populations (young, elderly people, pregnant women, and men) as indicated by their website labels. To ensure the generalisability of our model, we chose to develop a sparse Bayesian machine learning classifier using Relevance Vector Machine (RVM). Results: Using optimisation and normalisation techniques, we developed a best-performing classifier through joint optimisation of natural language features and min-max normalisation of feature frequencies. The AUC (0.957), sensitivity (0.900), and specificity (0.953) of the best model were statistically higher (p < 0.05) than other models using parallel optimisation of structural and semantic features with or without feature normalisation. We subsequently evaluated the diagnostic utility of our model in the clinic by comparing its positive (LR+) and negative likelihood ratios (LR−) and 95% confidence intervals (95% C.I.) as we adjusted the probability thresholds with the range of 0.1 and 0.9. We found that the best pair of LR+ (18.031, 95% C.I.: 10.992, 29.577) and LR− (0.100, 95% C.I.: 0.068, 0.148) was found when the probability threshold was set to 0.45 associated with a sensitivity of 0.905 (95%: 0.867, 0.942) and specificity of 0.950 (95% C.I.: 0.925, 0.975). These statistical properties of our model suggested its applicability in the clinic. Conclusion: Our study found that PAS had significant advantage over GEN mental health information regarding information actionability, engagement, and suitability for specific populations with distinct mental health issues. GEN is more suitable for general mental health information acquisition, whereas PAS can effectively engage patients and provide more effective and needed self-care support. The Bayesian machine learning classifier developed provided automatic tools to support decision making in the clinic to identify more actionable resources, effective to support self-care among different populations.

Use of Machine Learning Algorithms to Predict the Understandability of Health Education Materials: Development and Evaluation Study.

BackgroundImproving the understandability of health information can significantly increase the cost-effectiveness and efficiency of health education programs for vulnerable populations. There is a pressing need to develop clinically informed computerized tools to enable rapid, reliable assessment of the linguistic understandability of specialized health and medical education resources. This paper fills a critical gap in current patient-oriented health resource development, which requires reliable and accurate evaluation instruments to increase the efficiency and cost-effectiveness of health education resource evaluation.ObjectiveWe aimed to translate internationally endorsed clinical guidelines to machine learning algorithms to facilitate the evaluation of the understandability of health resources for international students at Australian universities.MethodsBased on international patient health resource assessment guidelines, we developed machine learning algorithms to predict the linguistic understandability of health texts for Australian college students (aged 25-30 years) from non-English speaking backgrounds. We compared extreme gradient boosting, random forest, neural networks, and C5.0 decision tree for automated health information understandability evaluation. The 5 machine learning models achieved statistically better results compared to the baseline logistic regression model. We also evaluated the impact of each linguistic feature on the performance of each of the 5 models.ResultsWe found that information evidentness, relevance to educational purposes, and logical sequence were consistently more important than numeracy skills and medical knowledge when assessing the linguistic understandability of health education resources for international tertiary students with adequate English skills (International English Language Testing System mean score 6.5) and high health literacy (mean 16.5 in the Short Assessment of Health Literacy-English test). Our results challenge the traditional views that lack of medical knowledge and numerical skills constituted the barriers to the understanding of health educational materials.ConclusionsMachine learning algorithms were developed to predict health information understandability for international college students aged 25-30 years. Thirteen natural language features and 5 evaluation dimensions were identified and compared in terms of their impact on the performance of the models. Health information understandability varies according to the demographic profiles of the target readers, and for international tertiary students, improving health information evidentness, relevance, and logic is critical.

SGANRDA: semi-supervised generative adversarial networks for predicting circRNA-disease associations.

Emerging research shows that circular RNA (circRNA) plays a crucial role in the diagnosis, occurrence and prognosis of complex human diseases. Compared with traditional biological experiments, the computational method of fusing multi-source biological data to identify the association between circRNA and disease can effectively reduce cost and save time. Considering the limitations of existing computational models, we propose a semi-supervised generative adversarial network (GAN) model SGANRDA for predicting circRNA-disease association. This model first fused the natural language features of the circRNA sequence and the features of disease semantics, circRNA and disease Gaussian interaction profile kernel, and then used all circRNA-disease pairs to pre-train the GAN network, and fine-tune the network parameters through labeled samples. Finally, the extreme learning machine classifier is employed to obtain the prediction result. Compared with the previous supervision model, SGANRDA innovatively introduced circRNA sequences and utilized all the information of circRNA-disease pairs during the pre-training process. This step can increase the information content of the feature to some extent and reduce the impact of too few known associations on the model performance. SGANRDA obtained AUC scores of 0.9411 and 0.9223 in leave-one-out cross-validation and 5-fold cross-validation, respectively. Prediction results on the benchmark dataset show that SGANRDA outperforms other existing models. In addition, 25 of the top 30 circRNA-disease pairs with the highest scores of SGANRDA in case studies were verified by recent literature. These experimental results demonstrate that SGANRDA is a useful model to predict the circRNA-disease association and can provide reliable candidates for biological experiments.

Linkage of primary care prescribing records and pharmacy dispensing Records in the Salford Lung Study: application in asthma

BackgroundRecords of medication prescriptions can be used in conjunction with pharmacy dispensing records to investigate the incidence of adherence, which is defined as observing the treatment plans agreed between a patient and their clinician. Using prescribing records alone fails to identify primary non-adherence; medications not being collected from the dispensary. Using dispensing records alone means that cases of conditions that resolve and/or treatments that are discontinued will be unaccounted for. While using a linked prescribing and dispensing dataset to measure medication non-adherence is optimal, this linkage is not routinely conducted. Furthermore, without a unique common event identifier, linkage between these two datasets is not straightforward.MethodsWe undertook a secondary analysis of the Salford Lung Study dataset. A novel probabilistic record linkage methodology was developed matching asthma medication pharmacy dispensing records and primary care prescribing records, using semantic (meaning) and syntactic (structure) harmonization, domain knowledge integration, and natural language feature extraction. Cox survival analysis was conducted to assess factors associated with the time to medication dispensing after the prescription was written. Finally, we used a simplified record linkage algorithm in which only identical records were matched, for a naïve benchmarking to compare against the results of our proposed methodology.ResultsWe matched 83% of pharmacy dispensing records to primary care prescribing records. Missing data were prevalent in the dispensing records which were not matched – approximately 60% for both medication strength and quantity. A naïve benchmarking approach, requiring perfect matching, identified one-quarter as many matching prescribing records as our methodology. Factors associated with delay (or failure) to collect the prescribed medication from a pharmacy included season, quantity of medication prescribed, previous dispensing history and class of medication. Our findings indicate that over 30% of prescriptions issued were not collected from a dispensary (primary non-adherence).ConclusionsWe have developed a probabilistic record linkage methodology matching a large percentage of pharmacy dispensing records with primary care prescribing records for asthma medications. This will allow researchers to link datasets in order to extract information about asthma medication non-adherence.

Философский язык И. Канта и Ж.-П. Сартра: концепты-смыслы и концепты-складки

The subject of the research is the features of the philosophical language of I. Kant and J.-P. Sartre in the context of the problematics of the complexity of the philosophical language as such and external linguistic features of natural languages. The aim of the work is a comparative analysis of the philosophical language of Kant and Sartre. The attention is focused on their epistemological and ethical discourse. First of all, the author concentrates on the specifics of such conceptual constructs as the concept of meanings and concept of the fold, as well as on which lexemes Kant and Sartre’s texts can be appropriately identified. The complexity of the language of both philosophers is emphasized and illustrated, its reasons are specified. The different type of complexity of the philosophical language of Kant and Sartre, as the author shows, can be productively recognized in the context of his distinction between concept-meanings and concept-folds. The conclusion that the complexity of the languages of the compared philosophers is caused by various reasons has been made. In the case of Kant, the very system of concept-meanings is complex; in the case of Sartre, the complexity of the introduced concept-folds is sometimes added.

What Is the Sense in Logic and Philosophy of Language

In the paper, various notions of the logical semiotic sense of linguistic expressions – namely, syntactic and semantic, intensional and extensional – are considered and formalised on the basis of a formal-logical conception of any language L characterised categorially in the spirit of certain Husserl's ideas of pure grammar, Leśniewski-Ajdukiewicz's theory of syntactic/semantic categories and, in accordance with Frege's ontological canons, Bocheński's and some of Suszko's ideas of language adequacy of expressions of L. The adequacy ensures their unambiguous syntactic and semantic senses and mutual, syntactic and semantic correspondence guaranteed by the acceptance of a postulate of categorial compatibility of syntactic and semantic (extensional and intensional) categories of expressions of L. This postulate defines the unification of these three logical senses. There are three principles of compositionality which follow from this postulate: one syntactic and two semantic ones already known to Frege. They are treated as conditions of homomorphism of partial algebra of L into algebraic models of L: syntactic, intensional and extensional. In the paper, they are applied to some expressions with quantifiers. Language adequacy connected with the logical senses described in the logical conception of language L is, obviously, an idealisation. The syntactic and semantic unambiguity of its expressions is not, of course, a feature of natural languages, but every syntactically and semantically ambiguous expression of such languages may be treated as a schema representing all of its interpretations that are unambiguous expressions.

What is Life?

In searching for life in extraterrestrial space, it is essential to act based on an unequivocal definition of life. In the 20th century, life was defined as cells that self-replicate, metabolize and are open for mutations, without which genetic information would remain unchangeable and evolution would be impossible. Current definitions of life derive from statistical mechanics, physics and chemistry of the 20th century in which life is considered to function machine-like, ignoring a central role of communication. Recent observations show that context dependent meaningful communication and network formation (and control) are central to all life forms. Evolutionary relevant new nucleotide sequences now appear to have originated from social agents such as viruses, their parasitic relatives and related RNA-networks, not from errors. By applying the known features of natural languages and communication, a new 21st century definition of life can be reached in which communicative interactions are central to all processes of life. A new definition of life must integrate the current empirical knowledge about interactions between cells, viruses, and RNA-networks to provide a better explanatory power than the 20th-century narrative.

Realism and Lexical Flexibility

AbstractMetaphysical investigation often proceeds by way of linguistic meaning. This tradition relies on an assumption about meanings, namely that they can be given in terms of referential relations and truth. Chomsky and others have illustrated the difficulty with this externalist hypothesis regarding natural language meanings, which implies that natural languages are ill‐suited for the purposes of metaphysical investigation. In reply to this discordance between the features of natural languages and the goals of metaphysical investigation, metaphysicians propose that we look to the invented languages used to express our best scientific theories as metaphysical guides, in the hope that these languages are better behaved. I argue that this retreat is beset with similar troubles for the metaphysician. In particular, I argue that central terms in the field of biology, namely ‘gene’ and ‘species’, exhibit a kind of lexical flexibility that renders them, much like their natural language counterparts, ill‐suited for the metaphysician's aims.

NLPEI: A Novel Self-Interacting Protein Prediction Model Based on Natural Language Processing and Evolutionary Information

The study of protein self-interactions (SIPs) can not only reveal the function of proteins at the molecular level, but is also crucial to understand activities such as growth, development, differentiation, and apoptosis, providing an important theoretical basis for exploring the mechanism of major diseases. With the rapid advances in biotechnology, a large number of SIPs have been discovered. However, due to the long period and high cost inherent to biological experiments, the gap between the identification of SIPs and the accumulation of data is growing. Therefore, fast and accurate computational methods are needed to effectively predict SIPs. In this study, we designed a new method, NLPEI, for predicting SIPs based on natural language understanding theory and evolutionary information. Specifically, we first understand the protein sequence as natural language and use natural language processing algorithms to extract its features. Then, we use the Position-Specific Scoring Matrix (PSSM) to represent the evolutionary information of the protein and extract its features through the Stacked Auto-Encoder (SAE) algorithm of deep learning. Finally, we fuse the natural language features of proteins with evolutionary features and make accurate predictions by Extreme Learning Machine (ELM) classifier. In the SIPs gold standard data sets of human and yeast, NLPEI achieved 94.19% and 91.29% prediction accuracy. Compared with different classifier models, different feature models, and other existing methods, NLPEI obtained the best results. These experimental results indicated that NLPEI is an effective tool for predicting SIPs and can provide reliable candidates for biological experiments.

TÜRKİYE TÜRKÇESİNDE KALIPLAŞMA

Creativity and originality are, as is well-known, the most distinct features of natural languages. Someone can easily form phrases or sentences that never said or heard before by putting lexical items from the lexicon of a language together in accordance with grammatical rules. However, a significant part of the lexicon of a language is made out of formulaic language units (proverbs, idioms, compounds, reduplications and formulaic expressions) and speakers of a language frequently put to use these units in communication. Therefore, it has to be stated that formulaicity is a reality in language besides creativity and originality. Even so researchers have not given much attention to general features of formulaicty and its place in language. Some formulaic language units are described as exception and some others are called as cliches without careful research. It is a necessity to describe the features of formulaicity in detail to explain functioning of language and its use. This paper will deal with the definition of formulaicity, its features and forms, and types of forulaicity. It is expected that this study will contribute to the description of formulaicity from various aspects.

Young children spontaneously recreate core properties of language in a new modality

How the world's 6,000+ natural languages have arisen is mostly unknown. Yet, new sign languages have emerged recently among deaf people brought together in a community, offering insights into the dynamics of language evolution. However, documenting the emergence of these languages has mostly consisted of studying the end product; the process by which ad hoc signs are transformed into a structured communication system has not been directly observed. Here we show how young children create new communication systems that exhibit core features of natural languages in less than 30 min. In a controlled setting, we blocked the possibility of using spoken language. In order to communicate novel messages, including abstract concepts, dyads of children spontaneously created novel gestural signs. Over usage, these signs became increasingly arbitrary and conventionalized. When confronted with the need to communicate more complex meanings, children began to grammatically structure their gestures. Together with previous work, these results suggest that children have the basic skills necessary, not only to acquire a natural language, but also to spontaneously create a new one. The speed with which children create these structured systems has profound implications for theorizing about language evolution, a process which is generally thought to span across many generations, if not millennia.

Homogeneity effects in natural language semantics.

Natural language sentences in which a property is ascribed to a plurality of objects have truth conditions that are not complementary with the truth conditions of the negations of such sentences. Starting from this observation, this paper presents an overview of so‐called homogeneity effects. Arguably a pervasive feature of natural language, homogeneity has reflexes in various domains and opens up a prospect for a unified analysis of phenomena that were hitherto viewed in quite different terms.

Values statements

Purpose This paper aims to examine 611 values statements to determine if values statements contain characteristics of organizational culture as provided by Denison and Mishra (1995). The general hypothesis given is there is a relationship between values statements and culture characteristics. Four testable hypotheses, one for each of Denison and Mishra’s (1995) characteristics, are created and tested. Design/methodology/approach The process in testing the hypotheses had two components. First, a taxonomy of the values statements had to be determined. This involved using natural language characteristics rather than predetermined classes to create a taxonomy based on the language itself. Second, a custom dictionary for each characteristic had to be created based on Neuendorf (2017) to perform content analysis. Once the values statements were coded with a taxonomic classification and with culture characteristics, a Chi-Square test was performed to determine a relationship between the statement type and the cultural characteristic, and then a multinomial regression test was performed to determine strength and direction of the relationships. Findings The tests for all four hypotheses produced significant results in the Chi-Square test. The multinomial regression tests showed primarily that Business statements types often lack adaptability and stakeholder involvement cultural elements. Additionally, Religion statement types are positively related to adaptability and mission. Research limitations/implications This paper creates a taxonomy and supplies the rules for classification. Values statements can now be classified using those rules and the classification used in analysis. Additionally, as values statements span over organizational culture, strategic management and strategic communication, these statements become a focal point for studying multiple topics across these fields. More particularly, finding the negative relationship between the Adaptability characteristic with the Business statement type and the involvement characteristic with the Business statement type may provide a cultural explanation for many mixed result studies on organizational success. Practical implications Organizational culture can be displayed by way of values statements and can potentially affect organizational strategy and organizational communication. Wording is extremely important in creating a values statement, and that statement must clearly reflect the cultural values of the organization. Originality/value First, this paper creates a taxonomy of values statements that is far more complete than anything created before. Second, by examining language, this paper discovers a link between organizational culture, strategic management and strategic communication.

A relevance-theoretical perspective on the question of why Jesus never wrote a book

Many reasons have been given for why Jesus never wrote anything. Some have argued that this was because he, or his audience, was illiterate; some that it was because Jewish rabbis only gave oral teaching; others that it was to avoid the idolatrizing of a divinely authored book. Moreover, given the deep reverence among the Jews for the written word found in the Torah, and the fact that Jesus claimed for himself the same authority as that upon which the Torah was based, it would seem legitimate to ask the question: why did he not seek to displace the Torah by a book of an equivalent or greater authority, like that claimed for the Koran in the Islamic tradition? The goal of this paper will be to bring to the table some linguistic arguments for why Jesus never committed any of his teachings to writing based on certain characteristics of natural language that have been highlighted by Relevance Theory, namely the underspecified nature of linguistic meaning and the consequent need for some way of narrowing down the range of possible interpretations of an utterance, as well as on the decontextualized character of written language.

A systematic review on deep learning architectures and applications

AbstractThe amount of digital data in the universe is growing at an exponential rate, doubling every 2 years, and changing how we live in the world. The information storage capacity and data requirement crossed the zettabytes. With this level of bombardment of data on machine learning techniques, it becomes very difficult to carry out parallel computations. Deep learning is broadening its scope and gaining more popularity in natural language processing, feature extraction and visualization, and almost in every machine learning trend. The purpose of this study is to provide a brief review of deep learning architectures and their working. Research papers and proceedings of conferences from various authentic resources (Institute of Electrical and Electronics Engineers, Wiley, Nature, and Elsevier) are studied and analyzed. Different architectures and their effectiveness to solve domain specific problems are evaluated. Various limitations and open problems of current architectures are discussed to provide better insights to help researchers and student to resume their research on these issues. One hundred one articles were reviewed for this meta‐analysis of deep learning. From this analysis, it is concluded that advanced deep learning architectures are combinations of few conventional architectures. For example, deep belief network and convolutional neural network are used to build convolutional deep belief network, which has higher capabilities than the parent architectures. These combined architectures are more robust to explore the problem space and thus can be the answer to build a general‐purpose architecture.

A Contemporary Survey of Machine Learning Techniques for Fake News Identification

Fake News is a grave problem in the society. The excessive reli-ance of people on internet for news is a huge motivation for spreading fake news on the internet and social media that creates a need for differentiat-ing it from the real. To fill this security void, various Machine Learning, Artificial Intelligence, Natural Language Processing and other related in-formation and technology tools are currently being researched to segregate one from another. In this paper, we establish fake news as a problem, study the classification of fake news into different types, methods of classifying news as fake or real with excessively studying ‘Style Based’ methods. We will also study about the machine learning and natural language features and metrics that are used in classification and see how machine learning can be applied to check this problem. Finally, we will be applying some of these methods on Indian news and find out how they perform.

Software for Creating Tutorials and Examinations on Natural Languages

Currently, philologists often use various software in studying and testing foreign languages. This work presents the software for creating tutorials and exams by philologists independently from software developers. To cover various features of natural languages and involve more abilities of users, such tutorials and exams contain randomly generated tasks of different types. Both questions and answers of the tasks can be text, graphic, sound, or combined. This software implements the algorithmic programming language for creating randomly generated (parameterized) tasks. The paper describes the objects, the syntax, and the procedure for generating random tasks in this programming language. The developed software is tested and used in secondary and higher educational institutions.