Search results for: semantic categories

Authors: Omid Shahmirzadi, Adam Lugowski, Kenneth Younge

Abstract:

Automatic measurement of semantic text similarity is an important task in natural language processing. In this paper, we evaluate the performance of different vector space models to perform this task. We address the real-world problem of modeling patent-to-patent similarity and compare TFIDF (and related extensions), topic models (e.g., latent semantic indexing), and neural models (e.g., paragraph vectors). Contrary to expectations, the added computational cost of text embedding methods is justified only when: 1) the target text is condensed; and 2) the similarity comparison is trivial. Otherwise, TFIDF performs surprisingly well in other cases: in particular for longer and more technical texts or for making finer-grained distinctions between nearest neighbors. Unexpectedly, extensions to the TFIDF method, such as adding noun phrases or calculating term weights incrementally, were not helpful in our context.

Keywords: big data, patent, text embedding, text similarity, vector space model

Procedia PDF Downloads 140

Authors: Haluk Eren, Mucahit Karaduman

Abstract:

This paper presents 15-year trends for scientific studies in a scientific database considering 3D and vehicle words. Two words are selected to find their associated publications in IEEE scholar database. Both of keywords are entered individually for the years 2002, 2012, and 2016 on the database to identify the preferred subjects of researchers in same years. We have classified closer research fields after searching and listing. Three years (2002, 2012, and 2016) have been investigated to figure out progress in specified time intervals. The first one is assumed as the initial progress in between 2002-2012, and the second one is in 2012-2016 that is fast development duration. We have found very interesting and beneficial results to understand the scholars’ research field preferences for a decade. This information will be highly desirable in smart city-based research purposes consisting of 3D and vehicle-related issues.

Keywords: Vehicle, three-dimensional, smart city, scholarly search, semantic

Procedia PDF Downloads 293

Authors: Deon de Jager, Yahya Zweiri, Dimitrios Makris

Abstract:

The three most important components in the cognitive architecture for cognitive robotics is memory representation, memory recall, and action-selection performed by the executive. In this paper, action selection, performed by the executive, is defined as a memory quantification and optimization process. The methodology describes the real-time construction of episodic memory through semantic memory optimization. The optimization is performed by set-based particle swarm optimization, using an adaptive entropy memory quantification approach for fitness evaluation. The performance of the approach is experimentally evaluated by simulation, where a UAV is tasked with the collection and delivery of a medical package. The experiments show that the UAV dynamically uses the episodic memory to autonomously control its velocity, while successfully completing its mission.

Keywords: cognitive robotics, semantic memory, episodic memory, maximum entropy principle, particle swarm optimization

Procedia PDF Downloads 119

Authors: Yingxu Wang, Jianhua Lu, Jun Peng, Jiawei Zhang

Abstract:

The fundamental demand in contemporary intelligent science towards Autonomous AI (AI*) is the creation of unprecedented formal means of Intelligent Mathematics (IM). It is discovered that natural intelligence is inductively created rather than exhaustively trained. Therefore, IM is a family of algebraic and denotational mathematics encompassing Inference Algebra, Real-Time Process Algebra, Concept Algebra, Semantic Algebra, Visual Frame Algebra, etc., developed in our labs. IM plays indispensable roles in training-free AI* theories and systems beyond traditional empirical data-driven technologies. A set of applications of IM-driven AI* systems will be demonstrated in contemporary intelligence science, AI*, and cognitive computers.

Keywords: intelligence mathematics, foundations of intelligent science, autonomous AI, cognitive computers, inference algebra, real-time process algebra, concept algebra, semantic algebra, applications

Procedia PDF Downloads 21

Authors: Ghazal Faraj, András Micsik

Abstract:

Shapes Constraint Language (SHACL), a World Wide Web Consortium (W3C) language, provides well-defined shapes and RDF graphs, named "shape graphs". These shape graphs validate other resource description framework (RDF) graphs which are called "data graphs". The structural features of SHACL permit generating a variety of conditions to evaluate string matching patterns, value type, and other constraints. Moreover, the framework of SHACL supports high-level validation by expressing more complex conditions in languages such as SPARQL protocol and RDF Query Language (SPARQL). SHACL includes two parts: SHACL Core and SHACL-SPARQL. SHACL Core includes all shapes that cover the most frequent constraint components. While SHACL-SPARQL is an extension that allows SHACL to express more complex customized constraints. Validating the efficacy of dataset mapping is an essential component of reconciled data mechanisms, as the enhancement of different datasets linking is a sustainable process. The conventional validation methods are the semantic reasoner and SPARQL queries. The former checks formalization errors and data type inconsistency, while the latter validates the data contradiction. After executing SPARQL queries, the retrieved information needs to be checked manually by an expert. However, this methodology is time-consuming and inaccurate as it does not test the mapping model comprehensively. Therefore, there is a serious need to expose a new methodology that covers the entire validation aspects for linking and mapping diverse datasets. Our goal is to conduct a new approach to achieve optimal validation outcomes. The first step towards this goal is implementing SHACL to validate the mapping between the International Committee for Documentation (CIDOC) conceptual reference model (CRM) and one of its ontologies. To initiate this project successfully, a thorough understanding of both source and target ontologies was required. Subsequently, the proper environment to run SHACL and its shape graphs were determined. As a case study, we performed SHACL over a CIDOC-CRM dataset after running a Pellet reasoner via the Protégé program. The applied validation falls under multiple categories: a) data type validation which constrains whether the source data is mapped to the correct data type. For instance, checking whether a birthdate is assigned to xsd:datetime and linked to Person entity via crm:P82a_begin_of_the_begin property. b) Data integrity validation which detects inconsistent data. For instance, inspecting whether a person's birthdate occurred before any of the linked event creation dates. The expected results of our work are: 1) highlighting validation techniques and categories, 2) selecting the most suitable techniques for those various categories of validation tasks. The next plan is to establish a comprehensive validation model and generate SHACL shapes automatically.

Keywords: SHACL, CIDOC-CRM, SPARQL, validation of ontology mapping

Procedia PDF Downloads 227

Authors: Joseph Gear, Yue Xu, Ernest Foo, Praveen Gauravaran, Zahra Jadidi, Leonie Simpson

Abstract:

Deep learning methods have been seeing an increasing application to the long-standing security research goal of automatic vulnerability detection for source code. Attention, however, must still be paid to the task of producing vector representations for source code (code embeddings) as input for these deep learning models. Graphical representations of code, most predominantly Abstract Syntax Trees and Code Property Graphs, have received some use in this task of late; however, for very large graphs representing very large code snip- pets, learning becomes prohibitively computationally expensive. This expense may be reduced by intelligently pruning this input to only vulnerability-relevant information; however, little research in this area has been performed. Additionally, most existing work comprehends code based solely on the structure of the graph at the expense of the information contained by the node in the graph. This paper proposes Semantic-enhanced Code Embedding for Vulnerability Discovery (SCEVD), a deep learning model which uses semantic-based feature selection for its vulnerability classification model. It uses information from the nodes as well as the structure of the code graph in order to select features which are most indicative of the presence or absence of vulnerabilities. This model is implemented and experimentally tested using the SARD Juliet vulnerability test suite to determine its efficacy. It is able to improve on existing code graph feature selection methods, as demonstrated by its improved ability to discover vulnerabilities.

Keywords: code representation, deep learning, source code semantics, vulnerability discovery

Procedia PDF Downloads 128

Authors: René A. Sørensen, Søren Skovsen, Peter Christiansen, Henrik Karstoft

Abstract:

Autonomous agricultural machines act in stochastic surroundings and therefore, must be able to perceive the surroundings in real time. This perception can be achieved using image sensors combined with advanced machine learning, in particular Deep Learning. Deep convolutional neural networks excel in labeling and perceiving color images and since the cost of high-quality RGB-cameras is low, the hardware cost of good perception depends heavily on memory and computation power. This paper investigates the possibility of designing lightweight convolutional neural networks for semantic segmentation (pixel wise classification) with reduced hardware requirements, to allow for embedded usage in autonomous agricultural machines. Using compression techniques, a lightweight convolutional neural network is designed to perform real-time semantic segmentation on an embedded platform. The network is trained on two large datasets, ImageNet and Pascal Context, to recognize up to 400 individual classes. The 400 classes are remapped into agricultural superclasses (e.g. human, animal, sky, road, field, shelterbelt and obstacle) and the ability to provide accurate real-time perception of agricultural surroundings is studied. The network is applied to the case of autonomous grass mowing using the NVIDIA Tegra X1 embedded platform. Feeding case-specific images to the network results in a fully segmented map of the superclasses in the image. As the network is still being designed and optimized, only a qualitative analysis of the method is complete at the abstract submission deadline. Proceeding this deadline, the finalized design is quantitatively evaluated on 20 annotated grass mowing images. Lightweight convolutional neural networks for semantic segmentation can be implemented on an embedded platform and show competitive performance with regards to accuracy and speed. It is feasible to provide cost-efficient perceptive capabilities related to semantic segmentation for autonomous agricultural machines.

Keywords: autonomous agricultural machines, deep learning, safety, visual perception

Procedia PDF Downloads 362

Authors: Jamal Abdi

Abstract:

This paper is largely a response/critique of Samuel P. Huntington´s Clash of Civilizations thesis. The overriding argument is that Huntington´s thesis is characterized by failure to distinguish between ´groups´ and ´categories´. Multinational civilizations overcoming their internal collective action problems, which would enable them to pursue a unified strategy vis-à-vis the West, is a rather foundational assumption in his theory. Without assigning sufficient intellectual attention to the processes through which multinational civilizations may gain capacity for concerted action i.e. become a group, he contended that the post-cold-war world would be shaped in large measure by interactions among seven or eight major civilizations. Thus, failure in providing a convincing analysis of multi-national civilizations´ transition from categories to groups is a significant weakness in Huntington´s clash theory. It is also suggested that so-called Islamic terrorism and the war on terror is not to be taken as an expression of presence of clash between a Western and an Islamic civilization, as terrorist organizations would be superfluous in a world characterized by clash of civilizations. Consequences of multinational civilizations becoming a group are discussed in relation to contemporary Western superiority.

Keywords: categories, civilizations, clash, groups, groupness

Procedia PDF Downloads 144

Authors: ShyamKrishna Kirithivasan, Shreyas Battula, Aditi Soori, Richa Ramesh, Ramamoorthy Srinath

Abstract:

The human brain, among the most complex and mysterious aspects of the body, harbors vast potential for extensive exploration. Unraveling these enigmas, especially within neural perception and cognition, delves into the realm of neural decoding. Harnessing advancements in generative AI, particularly in Visual Computing, seeks to elucidate how the brain comprehends visual stimuli observed by humans. The paper endeavors to reconstruct human-perceived visual stimuli using Functional Magnetic Resonance Imaging (fMRI). This fMRI data is then processed through pre-trained deep-learning models to recreate the stimuli. Introducing a new architecture named LatentNeuroNet, the aim is to achieve the utmost semantic fidelity in stimuli reconstruction. The approach employs a Latent Diffusion Model (LDM) - Stable Diffusion v1.5, emphasizing semantic accuracy and generating superior quality outputs. This addresses the limitations of prior methods, such as GANs, known for poor semantic performance and inherent instability. Text conditioning within the LDM's denoising process is handled by extracting text from the brain's ventral visual cortex region. This extracted text undergoes processing through a Bootstrapping Language-Image Pre-training (BLIP) encoder before it is injected into the denoising process. In conclusion, a successful architecture is developed that reconstructs the visual stimuli perceived and finally, this research provides us with enough evidence to identify the most influential regions of the brain responsible for cognition and perception.

Keywords: BLIP, fMRI, latent diffusion model, neural perception.

Procedia PDF Downloads 42

Authors: Mounia El Jaouhari, Mira Goral, Samir Diouny

Abstract:

Introduction: Previous research has indicated that language impairments are recognized as a feature of many neurodegenerative disorders, including non-language-led dementia subtypes such as Alzheimer´s disease (AD). In this preliminary study, the focal aim is to quantify the semantic content of naming and connected speech samples of Moroccan patients diagnosed with AD using two tasks taken from the culturally adapted and validated Moroccan version of the Boston Diagnostic Aphasia Examination. Methods: Five individuals with AD and five neurologically healthy individuals matched for age, gender, and education will participate in the study. Participants with AD will be diagnosed on the basis of the Moroccan version of the Diagnostic and Statistial Manual of Mental Disorders (DSM-4) screening test, the Moroccan version of the Mini Mental State Examination (MMSE) test scores, and neuroimaging analyses. The participants will engage in two tasks taken from the MDAE-SF: 1) Picture description and 2) Naming. Expected findings: Consistent with previous studies conducted on English speaking AD patients, we expect to find significant word production and retrieval impairments in AD patients in all measures. Moreover, we expect to find category fluency impairments that further endorse semantic breakdown accounts. In sum, not only will the findings of the current study shed more light on the locus of word retrieval impairments noted in AD, but also reflect the nature of Arabic morphology. In addition, the error patterns are expected to be similar to those found in previous AD studies in other languages.

Keywords: alzheimer's disease, anomia, connected speech, semantic impairments, moroccan arabic

Procedia PDF Downloads 118

Authors: Micah Amd

Abstract:

Preferences towards unfamiliar drink brands can be predictably influenced following correlations of subliminally-presented brands (CS) with positively valenced attributes (US). Alternatively, evaluations towards subliminally-presented CS may be more variable, suggesting that CS-evoked evaluations may disassociate from CS-associated preferences following subliminal CS-US conditioning. We assessed this hypothesis over three experiments (Ex1, Ex2, Ex3). Across each experiment, participants first provided preferences and evaluations towards meaningless trigrams (CS) as a baseline, followed by conditioning and a final round of preference and evaluation measurements. During conditioning, four pairs of subliminal and supraliminal/visible CS were respectively correlated with four US categories varying along aggregate valence (e.g., 100% positive, 80% positive, 40% positive, 0% positive – for Ex1 and Ex2). Across Ex1 and Ex2, presentation durations for subliminal CS were 34 and 17 milliseconds, respectively. Across Ex3, aggregate valences of the four US categories were altered (75% positive, 55% positive, 45% positive, 25% positive). Valence across US categories was manipulated to address a supplemental query of whether US-to-CS valence transfer was summative or integrative. During analysis, we computed two sets of difference scores reflecting pre-post preference and evaluation performances, respectively. These were subjected to Bayes tests. Across all experiments, results illustrated US-to-CS valence transfer was most likely to shift evaluations for visible CS, but least likely to shift evaluations for subliminal CS. Alternatively, preferences were likely to shift following correlations with single-valence categories (e.g., 100% positive, 100% negative) across both visible and subliminal CS. Our results suggest that CS preferences can be influenced through subliminal conditioning even as CS evaluations remain unchanged, supporting our central hypothesis. As for whether transfer effects are summative/integrative, our results were more mixed; a comparison of relative likelihoods revealed that preferences are more likely to reflect summative effects whereas evaluations reflect integration, independent of visibility condition.

Keywords: subliminal conditioning, evaluations, preferences, valence transfer

Procedia PDF Downloads 130

Authors: Sukjai Charoensuk, Penphan Pitaksongkram, Michael Christopher

Abstract:

Preliminary evidences supported the effectiveness of mindfulness-based interventions in reducing symptoms associated with a variety of medical and psychological conditions. However, the measurements of mindfulness are questionable since they have not been developed based-on Buddhist experiences. The purpose of this qualitative study was to describe meaning and cultivating factors of mindfulness as experienced by Thai females who practice Dhamma. Participants were purposively selected to include 2 groups of Thai females who practice Dhamma. The first group consisted of 6 female Buddhist monks, and the second group consisted of 7 female who practice Dhamma without ordaining. Data were collected using in-depth interview. The instruments used were demographic data questionnaire and guideline for in-depth interview developed by researchers. Content analysis was employed to analyze the data. The results revealed that Thai women who practice Dhamma described their experience in 2 themes, which were meaning and cultivating factors of mindfulness. The meaning composed of 4 categories; 1) Being Present, 2) Self-awareness, 3) Contemplation, and 4) Neutral. The cultivating factors of mindfulness composed of 2 categories; In-personal factors and Ex-personal factors. The In-personal cultivating factors included 4 sub-categories; Faith and Love, the Five Precepts, Sound body, and Practice. The Ex-personal cultivating factors included 2 sub-categories; Serenity, and Learning. These findings increase understanding about meaning of mindfulness and its cultivating factors. These could be used as a guideline to promote mental health and develop nursing interventions using mindfulness based, as well as, develop the instrument for assessing mindfulness in Thai context.

Keywords: cultivating factor, meaning of mindfulness, practice Dhamma, Thai women

Procedia PDF Downloads 321

Authors: Massra M. Sabeima, Myriam lamolle, Mohamedade Farouk Nanne

Abstract:

Adapting the learning resources of an e-learning system to the characteristics of the learners is an important aspect to consider when designing an adaptive e-learning system. However, this adaptation is not a simple process; it requires the extraction, analysis, and modeling of user information. This implies a good representation of the user's profile, which is the backbone of the adaptation process. Moreover, during the e-learning process, collaboration with similar users (same geographic province or knowledge context) is important. Productive collaboration motivates users to continue or not abandon the course and increases the assimilation of learning objects. The contribution of this work is the following: we propose an adaptive e-learning semantic platform to recommend learning resources to learners, using ontology to model the user profile and the course content, furthermore an implementation of a multi-agent system able to progressively generate the learning graph (taking into account the user's progress, and the changes that occur) for each user during the learning process, and to synchronize the users who collaborate on a learning object.

Keywords: adaptative learning, collaboration, multi-agent, ontology

Procedia PDF Downloads 145

Authors: Joana Portia Sakyi

Abstract:

The uniqueness of auxiliary verbs and their contribution to grammar as constituents, which act as preverbs to supply additional grammatical or functional meanings to clauses, are well established. Functionally, they relate clauses to tense, aspect, mood, voice, emphasis, and modality, along with the main verbs conveying the appropriate lexical content. There has been an issue in Akan grammar vis-à-vis the status of auxiliary verbs, in terms of whether Akan has auxiliaries or not and even which forms are to be regarded as auxiliaries. We investigate the syntactic, semantic, and pragmatic components of expressions and claim that Akan has auxiliary verbs that contribute the functional or grammatical meaning of modality, tense/aspect, etc., to clauses they occur in. Essentially, we use a self-created corpus data to consider the affix bέ- ‘may’, ‘must’, ‘should’; the form tùmí ‘can’, ‘be able to’; mà ‘to let’, ‘to allow’, ‘to permit’, ‘to make’, or ‘to cause’ someone to do something; the multi-word forms ὲsὲ sέ ‘must’, ‘should’ or ‘have to’ and ètwà sέ ‘must’, ‘should’ or ‘have to’, and assert that they are legitimate modal auxiliaries conveying epistemic, deontic, and dynamic modalities, as well as other meanings in the language.

Keywords: Akan, modality, modal auxiliaries, semantics

Procedia PDF Downloads 38

Authors: Hamed Azad, Azadeh M. Ardakani

Abstract:

Visual content, as an integral part of social media marketing, is growing dramatically. They are, in different technological usage categories (i.e., photos, graphics, animation IGTV, Stories, Livestreams, and Reels), associated with improving customer engagement behaviours (CEBs) in social commerce (SC). However, few researchers have explored the impact of specific and occasional contents that respect green products, gender equality, religious freedom, and LGBTs' rights. This study aims to compare and analyse how the ten best global brands (Interbrand's) in different categories communicate with customers on Instagram. Netnography approach and method used to conduct the data collection and data analysis of 1072 Instagram posts and 10494 comments. The results show that brands in fashion, sport, and homeware categories (H&M, Nike, and Ikea) emerge to use more effective content with the above global values elements than other brand categories. Findings also indicate that some different themes such as celebrities, models, pets, kids, aged and disabled people are part of visual management strategies on Instagram brands' pages. This research aims to inform researchers to consider all aspects of visual elements in content quality and marketing managers to increase brand optimisation, awareness, and authenticity by promoting contemporary world values on Instagram.

Keywords: green products, gender equality, religious freedom, LGBTs, Instagram, netnography

Procedia PDF Downloads 99

Authors: Chuluundorj Begz

Abstract:

This paper presents the dynamic, psycho-cognitive approach to study of human verbal thinking on the basis of typologically different languages /as a Mongolian, English and Russian/. Topological equivalence in verbal communication serves as a basis of Universality of mental structures and therefore deep structures. Mechanism of verbal thinking consisted at the deep level of basic concepts, rules for integration and classification, neural networks of vocabulary. In neuro cognitive study of language, neural architecture and neuro psychological mechanism of verbal cognition are basis of a vector-based modeling. Verbal perception and interpretation of the infinite set of meanings and propositions in mental continuum can be modeled by applying tensor methods. Euclidean and non-Euclidean spaces are applied for a description of human semantic vocabulary and high order structures.

Keywords: Euclidean spaces, isomorphism and homomorphism, mental lexicon, mental mapping, semantic memory, verbal cognition, vector space

Procedia PDF Downloads 490

Authors: Kehinde Augustina Odukoya

Abstract:

This study examines the portrayal of women in Nigerian magazine advertisements, with the aim to investigate whether there is sexualization of women in the advertisements. To achieve this aim, content analyses of 61 magazine advertisements from 5 different categories of magazines; a general interest magazine (Genevieve), fashion magazine (Hints Complete Fashion), men’s magazine (Mode), women’s magazine (Totally Whole) and a relationship magazine (Forever) were carried out. Erving Goffman’s 1979 frame analysis and Kang’s two additional coding categories were used to investigate the sexualization of women. Findings show that women are used for decorative purposes and objectified in over 70 per cent of the advertisements analyzed. Also, there is sexualization of women in magazine advertisements because women are nude 57.4 percent of the magazine advertisements.

Keywords: advertisements, magazine, sexualization, women

Procedia PDF Downloads 329

Authors: J. Bastos, P. Marques, S. Batterman, F. Freire

Abstract:

Due to demands of a growing urban population, it is crucial to manage urban development and its associated environmental impacts. While most of the environmental analyses have addressed buildings and transportation separately, both the design and location of a building affect environmental performance and focusing on one or the other can shift impacts and overlook improvement opportunities for more sustainable urban development. Recently, several life-cycle (LC) studies of residential buildings have integrated user transportation, focusing exclusively on primary energy demand and/or greenhouse gas emissions. Additionally, most papers considered only private transportation (mainly car). Although it is likely to have the largest share both in terms of use and associated impacts, exploring the variability associated with mode choice is relevant for comprehensive assessments and, eventually, for supporting decision-makers. This paper presents a life-cycle assessment (LCA) of a residential building in Lisbon (Portugal), addressing building construction, use and user transportation (commuting with private and public transportation). Five environmental indicators or categories are considered: (i) non-renewable primary energy (NRE), (ii) greenhouse gas intensity (GHG), (iii) eutrophication (EUT), (iv) acidification (ACID), and (v) ozone layer depletion (OLD). In a first stage, the analysis addresses the overall life-cycle considering the statistical model mix for commuting in the residence location. Then, a comparative analysis compares different available transportation modes to address the influence mode choice variability has on the results. The results highlight the large contribution of transportation to the overall LC results in all categories. NRE and GHG show strong correlation, as the three LC phases contribute with similar shares to both of them: building construction accounts for 6-9%, building use for 44-45%, and user transportation for 48% of the overall results. However, for other impact categories there is a large variation in the relative contribution of each phase. Transport is the most significant phase in OLD (60%); however, in EUT and ACID building use has the largest contribution to the overall LC (55% and 64%, respectively). In these categories, transportation accounts for 31-38%. A comparative analysis was also performed for four alternative transport modes for the household commuting: car, bus, motorcycle, and company/school collective transport. The car has the largest results in all impact categories. When compared to the overall LC with commuting by car, mode choice accounts for a variability of about 35% in NRE, GHG and OLD (the categories where transportation accounted for the largest share of the LC), 24% in EUT and 16% in ACID. NRE and GHG show a strong correlation because all modes have internal combustion engines. The second largest results for NRE, GHG and OLD are associated with commuting by motorcycle; however, for ACID and EUT this mode has better performance than bus and company/school transport. No single transportation mode performed best in all impact categories. Integrated assessments of buildings are needed to avoid shifts of impacts between life-cycle phases and environmental categories, and ultimately to support decision-makers.

Keywords: environmental impacts, LCA, Lisbon, transport

Procedia PDF Downloads 332

Authors: Shuo Liu, Dan Liu

Abstract:

In the field of named entity recognition, most of the research has been conducted around simple entities. However, for nested named entities, which still contain entities within entities, it has been difficult to identify them accurately due to their boundary ambiguity. In this paper, a hierarchical recognition model is constructed based on the grammatical structure and semantic features of Chinese text for boundary calculation based on lexical features. The analysis is carried out at different levels in terms of granularity, semantics, and lexicality, respectively, avoiding repetitive work to reduce computational effort and using the semantic features of words to calculate the boundaries of entities to improve the accuracy of the recognition work. The results of the experiments carried out on web-based microblogging data show that the model achieves an accuracy of 86.33% and an F1 value of 89.27% in recognizing nested named entities, making up for the shortcomings of some previous recognition models and improving the efficiency of recognition of nested named entities.

Keywords: coarse-grained, nested named entity, Chinese natural language processing, word embedding, T-SNE dimensionality reduction algorithm

Procedia PDF Downloads 97

Authors: Zaqiatul Mardiah, Afdol Tharik Wastono, Abdul Muta'ali

Abstract:

In general, the Arabic preposition ‘ala encodes the sense of UP-DOWN schema. However, the use of the preposition ‘ala can has many extended schemas that still have relation to its primary sense. In this paper, we show how the framework of cognitive linguistics (CL) based on image schemas can be applied to analyze the spatial semantic of the use of preposition ‘ala in the horizontal and vertical axes. The preposition ‘ala is usually used in the locative sense in which one physical entity is UP-DOWN relation to another physical entity. In spite of that, the cognitive analysis of ‘ala justifies the use of this preposition in many situations to seemingly encode non-up down-related spatial relations, and non-physical relation. This uncovers some of the unsolved issues concerning prepositions in general and the Arabic prepositions in particular the use of ‘ala as a sample. Using the Arabic corpus data, we reveal that in many cases and situations, the use of ‘ala is extended to depict relations other than the ones where the Trajector (TR) is actually in up-down relation to the Landmark (LM). The instances analyzed in this paper show that ‘ala encodes not only the spatial relations in which the TR and the LM are horizontally or vertically related to each other, but also non-spatial relations.

Keywords: image schema, preposition, spatial semantic, up-down relation

Procedia PDF Downloads 125

Authors: Alev Atak

Abstract:

In this paper, we aim to create a financial sentiment index by investigating the company’s voluntary information disclosures. We retrieve structured content from BIST 100 companies’ financial reports for the period 1998-2018 and extract relevant financial information for sentiment analysis through Natural Language Processing. We measure strategy-related disclosures and their cross-sectional variation and classify report content into generic sections using synonym lists divided into four main categories according to their liquidity risk profile, risk positions, intra-annual information, and exposure to risk. We use Word Error Rate and Cosin Similarity for comparing and measuring text similarity and derivation in sets of texts. In addition to performing text extraction, we will provide a range of text analysis options, such as the readability metrics, word counts using pre-determined lists (e.g., forward-looking, uncertainty, tone, etc.), and comparison with reference corpus (word, parts of speech and semantic level). Therefore, we create an adequate analytical tool and a financial dictionary to depict the importance of granular financial disclosure for investors to identify correctly the risk-taking behavior and hence make the aggregated effects traceable.

Keywords: financial sentiment, machine learning, information disclosure, risk

Procedia PDF Downloads 69

Authors: Jianwei Qian, Rob Law

Abstract:

With the expansion of globalization and the increment of market competition, the festival, especially the traditional one, has demonstrated its vitality under the new context. As a new tourist attraction, festivals play a critically important role in promoting the tourism economy, because the organization of a festival can engage more tourists, generate more revenues and win a wider media concern. However, in the current stage of China, traditional festivals as a way to disseminate national culture are undergoing the challenge of foreign festivals and the related culture. Different from those special events created solely for developing economy, traditional festivals have their own culture and connotation. Therefore, it is necessary to conduct a study on not only protecting the tradition, but promoting its development as well. This study conducts a comparative study of the development of China’s Valentine’s Day and Western Valentine’s Day under the Chinese context and centers on newspaper reports in China from 2000 to 2016. Based on the literature, two main research focuses can be established: one is concerned about the festival’s impact and the other is about tourists’ motivation to engage in a festival. Newspaper reports serve as the research discourse and can help cover the two focal points. With the assistance of content mining techniques, semantic networks for both Days are constructed separately to help depict the status quo of these two festivals in China. Based on the networks, two models are established to show the key component system of traditional festivals in the hope of perfecting the positive role festival tourism plays in the promotion of economy and culture. According to the semantic networks, newspaper reports on both festivals have similarities and differences. The difference is mainly reflected in its cultural connotation, because westerners and Chinese may show their love in different ways. Nevertheless, they share more common points in terms of economy, tourism, and society. They also have a similar living environment and stakeholders. Thus, they can be promoted together to revitalize some traditions in China. Three strategies are proposed to realize the aforementioned aim. Firstly, localize international festivals to suit the Chinese context to make it function better. Secondly, facilitate the internationalization process of traditional Chinese festivals to receive more recognition worldwide. Finally, allow traditional festivals to compete with foreign ones to help them learn from each other and elucidate the development of other festivals. It is believed that if all these can be realized, not only the traditional Chinese festivals can obtain a more promising future, but foreign ones are the same as well. Accordingly, the paper can contribute to the theoretical construction of festival images by the presentation of the semantic network. Meanwhile, the identified features and issues of festivals from two different cultures can enlighten the organization and marketing of festivals as a vital tourism activity. In the long run, the study can enhance the festival as a key attraction to keep the sustainable development of both the economy and the society.

Keywords: Chinese context, comparative study, festival tourism, semantic network analysis, valentine’s day

Procedia PDF Downloads 207

Authors: Bianca Suárez Puerta

Abstract:

Multimodal discourse refers to a method of study the media continuum between reality, screens as a device, audience, author, and media as a production from the audience. For this study we used semantic differential, a method proposed in the sixties by Osgood, Suci and Tannenbaum, starts from the assumption that under each particular way of perceiving the world, in each singular idea, there is a common cultural meaning that organizes experiences. In relation to these shared symbolic dimension, this method has had significant results, as it focuses on breaking down the meaning of certain significant acts into series of statements that place the subjects in front of some concepts. In Colombia, in 2016, a tool was designed to measure the meaning of a multimodal production, specially the acts of sense of transmedia productions that managed to receive funds from the Ministry of ICT of Colombia, and also, to analyze predictable patterns that can be found in calls and funds aimed at the production of culture in Colombia, in the context of the peace agreement, as a request for expressions from a hegemonic place, seeking to impose a worldview.

Keywords: semantic differential, semiotics, transmedia, critical analysis of discourse

Procedia PDF Downloads 180

Authors: M. Regina Carreira-Lopez

Abstract:

Lightweight ontologies seek to concrete union relationships between a parent node, and a secondary node, also called "child node". This logic relation (L) can be formally defined as a triple ontological relation (LO) equivalent to LO in ⟨LN, LE, LC⟩, and where LN represents a finite set of nodes (N); LE is a set of entities (E), each of which represents a relationship between nodes to form a rooted tree of ⟨LN, LE⟩; and LC is a finite set of concepts (C), encoded in a formal language (FL). Mondoc enables more refined searches on semantic and classified facets for retrieving specialized knowledge about Atlantic migrations, from the Declaration of Independence of the United States of America (1776) and to the end of the Spanish Civil War (1939). The model looks forward to increasing documentary relevance by applying an inverse frequency of co-ocurrent hypernymy phenomena for a concrete dataset of textual corpora, with RMySQL package. Mondoc profiles archival utilities implementing SQL programming code, and allows data export to XML schemas, for achieving semantic and faceted analysis of speech by analyzing keywords in context (KWIC). The methodology applies random and unrestricted sampling techniques with RMySQL to verify the resonance phenomena of inverse documentary relevance between the number of co-occurrences of the same term (t) in more than two documents of a set of texts (D). Secondly, the research also evidences co-associations between (t) and their corresponding synonyms and antonyms (synsets) are also inverse. The results from grouping facets or polysemic words with synsets in more than two textual corpora within their syntagmatic context (nouns, verbs, adjectives, etc.) state how to proceed with semantic indexing of hypernymy phenomena for subject-heading lists and for authority lists for documentary and archival purposes. Mondoc contributes to the development of web directories and seems to achieve a proper and more selective search of e-documents (classification ontology). It can also foster on-line catalogs production for semantic authorities, or concepts, through XML schemas, because its applications could be used for implementing data models, by a prior adaptation of the based-ontology to structured meta-languages, such as OWL, RDF (descriptive ontology). Mondoc serves to the classification of concepts and applies a semantic indexing approach of facets. It enables information retrieval, as well as quantitative and qualitative data interpretation. The model reproduces a triple tuple ⟨LN, LE, LT, LCF L, BKF⟩ where LN is a set of entities that connect with other nodes to concrete a rooted tree in ⟨LN, LE⟩. LT specifies a set of terms, and LCF acts as a finite set of concepts, encoded in a formal language, L. Mondoc only resolves partial problems of linguistic ambiguity (in case of synonymy and antonymy), but neither the pragmatic dimension of natural language nor the cognitive perspective is addressed. To achieve this goal, forthcoming programming developments should target at oriented meta-languages with structured documents in XML.

Keywords: hypernymy, information retrieval, lightweight ontology, resonance

Procedia PDF Downloads 101

Authors: Yihui Zou

Abstract:

The integration of the traditional landscape of the ancient city and the poet's emotions and symbolization into ancient poetry is the unique cultural gene and spiritual core of the historical city, and re-understanding the historical landscape pattern from the poetry is conducive to continuing the historical city context and improving the current situation of the gradual decline of the poetry of the modern historical urban landscape. Starting from Tang poetry, using semantic analysis methods combined with text mining technology, entry mining, word frequency analysis, and cluster analysis of the landscape information of Tang Chang'an City were carried out, and the method framework for analyzing the urban landscape form based on poetry text was constructed. Nearly 160 poems describing the landscape of Tang Chang'an City were screened, and the poetic landscape characteristics of Tang Chang'an City were sorted out locally in order to combine with modern urban spatial development to continue the urban spatial context.

Keywords: Tang Chang'an City, poetic texts, semantic analysis, historical landscape

Procedia PDF Downloads 11

Authors: Mikhail Zarechnev, Bora I. Kumova

Abstract:

A syllogism is a deductive inference scheme used to derive a conclusion from a set of premises. In a categorical syllogisms, there are only two premises and every premise and conclusion is given in form of a quantified relationship between two objects. The different order of objects in premises give classification known as figures. We have shown that the ordered combinations of 3 generalized quantifiers with certain figure provide in total of 108 syllogistic moods which can be considered as different inference rules. The classical syllogistic system allows to model human thought and reasoning with syllogistic structures always attracted the attention of cognitive scientists. Since automated reasoning is considered as part of learning subsystem of AI agents, syllogistic system can be applied for this approach. Another application of syllogistic system is related to inference mechanisms on the Semantic Web applications. In this paper we proposed the mathematical model and algorithm for syllogistic reasoning. Also the model of iterative syllogistic reasoning in case of continuous flows of incoming data based on case–based reasoning and possible applications of proposed system were discussed.

Keywords: categorical syllogism, case-based reasoning, cognitive architecture, inference on the semantic web, syllogistic reasoning

Procedia PDF Downloads 382

Authors: Hamideh Marefat, Eskandar Samadi

Abstract:

This study examined the effect of semantics on processing ambiguous sentences containing Relative Clauses (RCs) preceded by a complex Determiner Phrase (DP) by Persian-speaking learners of L2 English with different proficiency and Working Memory Capacities (WMCs). The semantic relationship studied was one between the subject of the main clause and one of the DPs in the complex DP to see if, as predicted by Spreading Activation Model, priming one of the DPs through this semantic manipulation affects the L2ers’ preference. The results of a task using Rapid Serial Visual Processing (time-controlled paradigm) showed that manipulation of the relationship between the subject of the main clause and one of the DPs in the complex DP preceding RC has no effect on the choice of the antecedent; rather, the L2ers' processing is guided by the phrase structure information. Moreover, while proficiency did not have any effect on the participants’ preferences, WMC brought about a difference in their preferences, with a DP1 preference by those with a low WMC. This finding supports the chunking hypothesis and the predicate proximity principle, which is the strategy also used by monolingual Persian speakers.

Keywords: semantics, relative clause processing, ambiguity resolution, proficiency, working memory capacity

Procedia PDF Downloads 594

Authors: Xiaoxiao Li, Shuangcheng Jia, Qian Li

Abstract:

Keypoint detection has always been a challenge in the field of image recognition. This paper proposes a novelty keypoint detection method which is called Multi-Scale Feature Fusion Convolutional Network with Attention (MFFCNA). We verified that the multi-scale features with the attention mechanism module have better feature expression capability. The feature fusion between different scales makes the information that the network model can express more abundant, and the network is easier to converge. On our self-made street sign corner dataset, we validate the MFFCNA model with an accuracy of 97.8% and a recall of 81%, which are 5 and 8 percentage points higher than the HRNet network, respectively. On the COCO dataset, the AP is 71.9%, and the AR is 75.3%, which are 3 points and 2 points higher than HRNet, respectively. Extensive experiments show that our method has a remarkable improvement in the keypoint recognition tasks, and the recognition effect is better than the existing methods. Moreover, our method can be applied not only to keypoint detection but also to image classification and semantic segmentation with good generality.

Keywords: keypoint detection, feature fusion, attention, semantic segmentation

Procedia PDF Downloads 92

Authors: Sunethra Jayathilake, Vathsala Jayasuriya-Illesinghe, Kerstin Samarasinghe, Himani Molligoda, Rasika Perera

Abstract:

In Sri Lanka, postnatal care in the state hospitals is provided by different professional categories: Midwifery trained registered nurses (MTRNs), Registered Nurses (RNs) who do not have midwifery training, doctors and midwives. Even though four professional categories provide postnatal care to mothers and newborn babies, they are not aware of their own tasks and responsibilities in postnatal care. Particularly MTRN’s role in the postnatal unit is unclear. The current study aimed to identify nurses’ (both MTRN and RNs) perception on MTRN’s tasks and responsibilities in postnatal care. This is a descriptive cross sectional study using postal survey. All nurses who were currently working in postnatal units at five selected tertiary care hospitals in the Western Province at that time were invited to participate in the study. Accordingly, the pre evaluated self-administered questionnaire was sent to 201 nurses (53 MTRNs and 148 RNs) in the study setting. The number of valid return questionnaire was 166; response rate was 83%. Respondents rated the responsibility of four professional categories: MTRN, RN, doctor and midwife whether they are 'primarily responsible', 'responsible in absence' and 'not responsible', for each of 15 postnatal (PN) tasks which were previously identified from focus group discussions with care providers during the first phase of the study. Data were analyzed using SPSS version 20; descriptive statistics were calculated. Out of the 15 PN tasks, 13 were identified as MTRNs’ primary responsibilities by 71%-93% of respondents. The respondents also considered six (6) tasks out of 15 as primary responsibility of both MTRN and RN, seven (7) tasks as primary responsibility of MTRN, RN and doctor and the remaining two (2) tasks were identified as the primary responsibility of MTRN, RN and midwife. All 15 PN tasks overlapped with other professional categories. Overlapping tasks may create role confusion leading to conflicts among professional categories which affect the quality of care they provide, eventually, threaten the safety of the client. It is recommended that an official job description for each care provider is needed to recognize their own professional boundaries for ensuring safe, quality care delivery in Sri Lanka.

Keywords: overlapping, postnatal, responsibilities, tasks

Procedia PDF Downloads 121

Authors: Zhaoxin Luo, Michael Zhu

Abstract:

In natural languages, there are always complex semantic hierarchies. Obtaining the feature representation based on these complex semantic hierarchies becomes the key to the success of the model. Several RNN models have recently been proposed to use latent indicators to obtain the hierarchical structure of documents. However, the model that only uses a single-layer latent indicator cannot achieve the true hierarchical structure of the language, especially a complex language like Chinese. In this paper, we propose a deep layered model that stacks arbitrarily many RNN layers equipped with latent indicators. After using EM and training it hierarchically, our model solves the computational problem of stacking RNN layers and makes it possible to stack arbitrarily many RNN layers. Our deep hierarchical model not only achieves comparable results to large pre-trained models on the Chinese short text classification problem but also achieves state of art results on the Chinese long text classification problem.

Keywords: nature language processing, recurrent neural network, hierarchical structure, document classification, Chinese

Procedia PDF Downloads 34