Search results for: latent semantic indexing
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 889

Search results for: latent semantic indexing

889 Topic Modelling Using Latent Dirichlet Allocation and Latent Semantic Indexing on SA Telco Twitter Data

Authors: Phumelele Kubheka, Pius Owolawi, Gbolahan Aiyetoro

Abstract:

Twitter is one of the most popular social media platforms where users can share their opinions on different subjects. As of 2010, The Twitter platform generates more than 12 Terabytes of data daily, ~ 4.3 petabytes in a single year. For this reason, Twitter is a great source for big mining data. Many industries such as Telecommunication companies can leverage the availability of Twitter data to better understand their markets and make an appropriate business decision. This study performs topic modeling on Twitter data using Latent Dirichlet Allocation (LDA). The obtained results are benchmarked with another topic modeling technique, Latent Semantic Indexing (LSI). The study aims to retrieve topics on a Twitter dataset containing user tweets on South African Telcos. Results from this study show that LSI is much faster than LDA. However, LDA yields better results with higher topic coherence by 8% for the best-performing model represented in Table 1. A higher topic coherence score indicates better performance of the model.

Keywords: big data, latent Dirichlet allocation, latent semantic indexing, telco, topic modeling, twitter

Procedia PDF Downloads 129
888 How to Perform Proper Indexing?

Authors: Watheq Mansour, Waleed Bin Owais, Mohammad Basheer Kotit, Khaled Khan

Abstract:

Efficient query processing is one of the utmost requisites in any business environment to satisfy consumer needs. This paper investigates the various types of indexing models, viz. primary, secondary, and multi-level. The investigation is done under the ambit of various types of queries to which each indexing model performs with efficacy. This study also discusses the inherent advantages and disadvantages of each indexing model and how indexing models can be chosen based on a particular environment. This paper also draws parallels between various indexing models and provides recommendations that would help a Database administrator to zero-in on a particular indexing model attributed to the needs and requirements of the production environment. In addition, to satisfy industry and consumer needs attributed to the colossal data generation nowadays, this study has proposed two novel indexing techniques that can be used to index highly unstructured and structured Big Data with efficacy. The study also briefly discusses some best practices that the industry should follow in order to choose an indexing model that is apposite to their prerequisites and requirements.

Keywords: indexing, hashing, latent semantic indexing, B-tree

Procedia PDF Downloads 134
887 Semantic Indexing Improvement for Textual Documents: Contribution of Classification by Fuzzy Association Rules

Authors: Mohsen Maraoui

Abstract:

In the aim of natural language processing applications improvement, such as information retrieval, machine translation, lexical disambiguation, we focus on statistical approach to semantic indexing for multilingual text documents based on conceptual network formalism. We propose to use this formalism as an indexing language to represent the descriptive concepts and their weighting. These concepts represent the content of the document. Our contribution is based on two steps. In the first step, we propose the extraction of index terms using the multilingual lexical resource Euro WordNet (EWN). In the second step, we pass from the representation of index terms to the representation of index concepts through conceptual network formalism. This network is generated using the EWN resource and pass by a classification step based on association rules model (in attempt to discover the non-taxonomic relations or contextual relations between the concepts of a document). These relations are latent relations buried in the text and carried by the semantic context of the co-occurrence of concepts in the document. Our proposed indexing approach can be applied to text documents in various languages because it is based on a linguistic method adapted to the language through a multilingual thesaurus. Next, we apply the same statistical process regardless of the language in order to extract the significant concepts and their associated weights. We prove that the proposed indexing approach provides encouraging results.

Keywords: concept extraction, conceptual network formalism, fuzzy association rules, multilingual thesaurus, semantic indexing

Procedia PDF Downloads 123
886 Multidimensional Item Response Theory Models for Practical Application in Large Tests Designed to Measure Multiple Constructs

Authors: Maria Fernanda Ordoñez Martinez, Alvaro Mauricio Montenegro

Abstract:

This work presents a statistical methodology for measuring and founding constructs in Latent Semantic Analysis. This approach uses the qualities of Factor Analysis in binary data with interpretations present on Item Response Theory. More precisely, we propose initially reducing dimensionality with specific use of Principal Component Analysis for the linguistic data and then, producing axes of groups made from a clustering analysis of the semantic data. This approach allows the user to give meaning to previous clusters and found the real latent structure presented by data. The methodology is applied in a set of real semantic data presenting impressive results for the coherence, speed and precision.

Keywords: semantic analysis, factorial analysis, dimension reduction, penalized logistic regression

Procedia PDF Downloads 420
885 Text Similarity in Vector Space Models: A Comparative Study

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 149
884 Recurrent Neural Networks with Deep Hierarchical Mixed Structures for Chinese Document Classification

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 43
883 Enhancement of Indexing Model for Heterogeneous Multimedia Documents: User Profile Based Approach

Authors: Aicha Aggoune, Abdelkrim Bouramoul, Mohamed Khiereddine Kholladi

Abstract:

Recent research shows that user profile as important element can improve heterogeneous information retrieval with its content. In this context, we present our indexing model for heterogeneous multimedia documents. This model is based on the combination of user profile to the indexing process. The general idea of our proposal is to operate the common concepts between the representation of a document and the definition of a user through his profile. These two elements will be added as additional indexing entities to enrich the heterogeneous corpus documents indexes. We have developed IRONTO domain ontology allowing annotation of documents. We will present also the developed tool validating the proposed model.

Keywords: indexing model, user profile, multimedia document, heterogeneous of sources, ontology

Procedia PDF Downloads 326
882 Parallel Querying of Distributed Ontologies with Shared Vocabulary

Authors: Sharjeel Aslam, Vassil Vassilev, Karim Ouazzane

Abstract:

Ontologies and various semantic repositories became a convenient approach for implementing model-driven architectures of distributed systems on the Web. SPARQL is the standard query language for querying such. However, although SPARQL is well-established standard for querying semantic repositories in RDF and OWL format and there are commonly used APIs which supports it, like Jena for Java, its parallel option is not incorporated in them. This article presents a complete framework consisting of an object algebra for parallel RDF and an index-based implementation of the parallel query engine capable of dealing with the distributed RDF ontologies which share common vocabulary. It has been implemented in Java, and for validation of the algorithms has been applied to the problem of organizing virtual exhibitions on the Web.

Keywords: distributed ontologies, parallel querying, semantic indexing, shared vocabulary, SPARQL

Procedia PDF Downloads 176
881 Lecture Video Indexing and Retrieval Using Topic Keywords

Authors: B. J. Sandesh, Saurabha Jirgi, S. Vidya, Prakash Eljer, Gowri Srinivasa

Abstract:

In this paper, we propose a framework to help users to search and retrieve the portions in the lecture video of their interest. This is achieved by temporally segmenting and indexing the lecture video using the topic keywords. We use transcribed text from the video and documents relevant to the video topic extracted from the web for this purpose. The keywords for indexing are found by applying the non-negative matrix factorization (NMF) topic modeling techniques on the web documents. Our proposed technique first creates indices on the transcribed documents using the topic keywords, and these are mapped to the video to find the start and end time of the portions of the video for a particular topic. This time information is stored in the index table along with the topic keyword which is used to retrieve the specific portions of the video for the query provided by the users.

Keywords: video indexing and retrieval, lecture videos, content based video search, multimodal indexing

Procedia PDF Downloads 229
880 Classification of Contexts for Mentioning Love in Interviews with Victims of the Holocaust

Authors: Marina Yurievna Aleksandrova

Abstract:

Research of the Holocaust retains value not only for history but also for sociology and psychology. One of the most important fields of study is how people were coping during and after this traumatic event. The aim of this paper is to identify the main contexts of the topic of love and to determine which contexts are more characteristic for different groups of victims of the Holocaust (gender, nationality, age). In this research, transcripts of interviews with Holocaust victims that were collected during 1946 for the "Voices of the Holocaust" project were used as data. Main contexts were analyzed with methods of network analysis and latent semantic analysis and classified by gender, age, and nationality with random forest. The results show that love is articulated and described significantly differently for male and female informants, nationality is shown results with lower values of quality metrics, as well as the age.

Keywords: Holocaust, latent semantic analysis, network analysis, text-mining, random forest

Procedia PDF Downloads 162
879 Lexico-Semantic and Contextual Analysis of the Concept of Joy in Modern English Fiction

Authors: Zarine Avetisyan

Abstract:

Concepts are part and parcel of everyday text and talk. Their ubiquity predetermines the topicality of the given research which aims at the semantic decomposition of concepts in general and the concept of joy in particular, as well as the study of lexico-semantic variants as means of realization of a certain concept in different “semantic settings”, namely in a certain context. To achieve the stated aim, the given research departs from the methods of componential and contextual analysis, studying lexico-semantic variants /LSVs/ of the concept of joy and the semantic signs embedded in those LSVs, such as the semantic sign of intensity, supporting emotions, etc. in the context of Modern English fiction.

Keywords: concept, context, lexico-semantic variant, semantic sign

Procedia PDF Downloads 335
878 Fuzzy Semantic Annotation of Web Resources

Authors: Sahar Maâlej Dammak, Anis Jedidi, Rafik Bouaziz

Abstract:

With the great mass of pages managed through the world, and especially with the advent of the Web, their manual annotation is impossible. We focus, in this paper, on the semiautomatic annotation of the web pages. We propose an approach and a framework for semantic annotation of web pages entitled “Querying Web”. Our solution is an enhancement of the first result of annotation done by the “Semantic Radar” Plug-in on the web resources, by annotations using an enriched domain ontology. The concepts of the result of Semantic Radar may be connected to several terms of the ontology, but connections may be uncertain. We represent annotations as possibility distributions. We use the hierarchy defined in the ontology to compute degrees of possibilities. We want to achieve an automation of the fuzzy semantic annotation of web resources.

Keywords: fuzzy semantic annotation, semantic web, domain ontologies, querying web

Procedia PDF Downloads 346
877 Semantic Search Engine Based on Query Expansion with Google Ranking and Similarity Measures

Authors: Ahmad Shahin, Fadi Chakik, Walid Moudani

Abstract:

Our study is about elaborating a potential solution for a search engine that involves semantic technology to retrieve information and display it significantly. Semantic search engines are not used widely over the web as the majorities are still in Beta stage or under construction. Many problems face the current applications in semantic search, the major problem is to analyze and calculate the meaning of query in order to retrieve relevant information. Another problem is the ontology based index and its updates. Ranking results according to concept meaning and its relation with query is another challenge. In this paper, we are offering a light meta-engine (QESM) which uses Google search, and therefore Google’s index, with some adaptations to its returned results by adding multi-query expansion. The mission was to find a reliable ranking algorithm that involves semantics and uses concepts and meanings to rank results. At the beginning, the engine finds synonyms of each query term entered by the user based on a lexical database. Then, query expansion is applied to generate different semantically analogous sentences. These are generated randomly by combining the found synonyms and the original query terms. Our model suggests the use of semantic similarity measures between two sentences. Practically, we used this method to calculate semantic similarity between each query and the description of each page’s content generated by Google. The generated sentences are sent to Google engine one by one, and ranked again all together with the adapted ranking method (QESM). Finally, our system will place Google pages with higher similarities on the top of the results. We have conducted experimentations with 6 different queries. We have observed that most ranked results with QESM were altered with Google’s original generated pages. With our experimented queries, QESM generates frequently better accuracy than Google. In some worst cases, it behaves like Google.

Keywords: semantic search engine, Google indexing, query expansion, similarity measures

Procedia PDF Downloads 403
876 Reconstruction of Visual Stimuli Using Stable Diffusion with Text Conditioning

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 50
875 Exploring Syntactic and Semantic Features for Text-Based Authorship Attribution

Authors: Haiyan Wu, Ying Liu, Shaoyun Shi

Abstract:

Authorship attribution is to extract features to identify authors of anonymous documents. Many previous works on authorship attribution focus on statistical style features (e.g., sentence/word length), content features (e.g., frequent words, n-grams). Modeling these features by regression or some transparent machine learning methods gives a portrait of the authors' writing style. But these methods do not capture the syntactic (e.g., dependency relationship) or semantic (e.g., topics) information. In recent years, some researchers model syntactic trees or latent semantic information by neural networks. However, few works take them together. Besides, predictions by neural networks are difficult to explain, which is vital in authorship attribution tasks. In this paper, we not only utilize the statistical style and content features but also take advantage of both syntactic and semantic features. Different from an end-to-end neural model, feature selection and prediction are two steps in our method. An attentive n-gram network is utilized to select useful features, and logistic regression is applied to give prediction and understandable representation of writing style. Experiments show that our extracted features can improve the state-of-the-art methods on three benchmark datasets.

Keywords: authorship attribution, attention mechanism, syntactic feature, feature extraction

Procedia PDF Downloads 114
874 A Contribution to the Polynomial Eigen Problem

Authors: Malika Yaici, Kamel Hariche, Tim Clarke

Abstract:

The relationship between eigenstructure (eigenvalues and eigenvectors) and latent structure (latent roots and latent vectors) is established. In control theory eigenstructure is associated with the state space description of a dynamic multi-variable system and a latent structure is associated with its matrix fraction description. Beginning with block controller and block observer state space forms and moving on to any general state space form, we develop the identities that relate eigenvectors and latent vectors in either direction. Numerical examples illustrate this result. A brief discussion of the potential of these identities in linear control system design follows. Additionally, we present a consequent result: a quick and easy method to solve the polynomial eigenvalue problem for regular matrix polynomials.

Keywords: eigenvalues/eigenvectors, latent values/vectors, matrix fraction description, state space description

Procedia PDF Downloads 441
873 Optimization Query Image Using Search Relevance Re-Ranking Process

Authors: T. G. Asmitha Chandini

Abstract:

Web-based image search re-ranking, as an successful method to get better the results. In a query keyword, the first stair is store the images is first retrieve based on the text-based information. The user to select a query keywordimage, by using this query keyword other images are re-ranked based on their visual properties with images.Now a day to day, people projected to match images in a semantic space which is used attributes or reference classes closely related to the basis of semantic image. though, understanding a worldwide visual semantic space to demonstrate highly different images from the web is difficult and inefficient. The re-ranking images, which automatically offline part learns dissimilar semantic spaces for different query keywords. The features of images are projected into their related semantic spaces to get particular images. At the online stage, images are re-ranked by compare their semantic signatures obtained the semantic précised by the query keyword image. The query-specific semantic signatures extensively improve both the proper and efficiency of image re-ranking.

Keywords: Query, keyword, image, re-ranking, semantic, signature

Procedia PDF Downloads 532
872 Herbal Based Fingerprint Powder Formulation for Latent Fingermark Visualization: Catechu (Kattha)

Authors: Pallavi Thakur, Rakesh K. Garg

Abstract:

Latent fingerprints are commonly encountered evidence at the scene of the crime. It is very important to decipher these fingerprints in order to explore their identity and a lot of research has been made on the visualization of latent fingermarks on various substrates by numerous researchers. During the past few years large number of powder formulations has been evolved for the development of latent fingermarks on different surfaces. This paper reports a new and simple fingerprint powder which is non-toxic and has been employed on different substrates successfully for the development and visualization of latent fingermarks upto the time period of twelve days in varying temperature conditions. In this study, a less expensive, simple and easily available catechu (kattha) powder has been used to decipher the latent fingermarks on different substrates namely glass, plastic, metal, aluminium foil, white paper, wall tile and wooden sheet. It is observed that it gives very clear results on all the mentioned substrates and can be successfully used for the development and visualization of twelve days old latent fingermarks in varying temperature conditions on wall tiles.

Keywords: fingermarks, catechu, visualization, aged fingermarks

Procedia PDF Downloads 167
871 Challenges over Two Semantic Repositories - OWLIM and AllegroGraph

Authors: Paria Tajabor, Azin Azarbani

Abstract:

The purpose of this research study is exploring two kind of semantic repositories with regards to various factors to find the best approaches that an artificial manager can use to produce ontology in a system based on their interaction, association and research. To this end, as the best way to evaluate each system and comparing with others is analysis, several benchmarking over these two repositories were examined. These two semantic repositories: OWLIM and AllegroGraph will be the main core of this study. The general objective of this study is to be able to create an efficient and cost-effective manner reports which is required to support decision making in any large enterprise.

Keywords: OWLIM, allegrograph, RDF, reasoning, semantic repository, semantic-web, SPARQL, ontology, query

Procedia PDF Downloads 242
870 A Semantic E-Learning and E-Assessment System of Learners

Authors: Wiem Ben Khalifa, Dalila Souilem, Mahmoud Neji

Abstract:

The evolutions of Social Web and Semantic Web lead us to ask ourselves about the way of supporting the personalization of learning by means of intelligent filtering of educational resources published in the digital networks. We recommend personalized courses of learning articulated around a first educational course defined upstream. Resuming the context and the stakes in the personalization, we also suggest anchoring the personalization of learning in a community of interest within a group of learners enrolled in the same training. This reflection is supported by the display of an active and semantic system of learning dedicated to the constitution of personalized to measure courses and in the due time.

Keywords: Semantic Web, semantic system, ontology, evaluation, e-learning

Procedia PDF Downloads 311
869 Compressed Suffix Arrays to Self-Indexes Based on Partitioned Elias-Fano

Authors: Guo Wenyu, Qu Youli

Abstract:

A practical and simple self-indexing data structure, Partitioned Elias-Fano (PEF) - Compressed Suffix Arrays (CSA), is built in linear time for the CSA based on PEF indexes. Moreover, the PEF-CSA is compared with two classical compressed indexing methods, Ferragina and Manzini implementation (FMI) and Sad-CSA on different type and size files in Pizza & Chili. The PEF-CSA performs better on the existing data in terms of the compression ratio, count, and locates time except for the evenly distributed data such as proteins data. The observations of the experiments are that the distribution of the φ is more important than the alphabet size on the compression ratio. Unevenly distributed data φ makes better compression effect, and the larger the size of the hit counts, the longer the count and locate time.

Keywords: compressed suffix array, self-indexing, partitioned Elias-Fano, PEF-CSA

Procedia PDF Downloads 231
868 Understanding the Interactive Nature in Auditory Recognition of Phonological/Grammatical/Semantic Errors at the Sentence Level: An Investigation Based upon Japanese EFL Learners’ Self-Evaluation and Actual Language Performance

Authors: Hirokatsu Kawashima

Abstract:

One important element of teaching/learning listening is intensive listening such as listening for precise sounds, words, grammatical, and semantic units. Several classroom-based investigations have been conducted to explore the usefulness of auditory recognition of phonological, grammatical and semantic errors in such a context. The current study reports the results of one such investigation, which targeted auditory recognition of phonological, grammatical, and semantic errors at the sentence level. 56 Japanese EFL learners participated in this investigation, in which their recognition performance of phonological, grammatical and semantic errors was measured on a 9-point scale by learners’ self-evaluation from the perspective of 1) two types of similar English sound (vowel and consonant minimal pair words), 2) two types of sentence word order (verb phrase-based and noun phrase-based word orders), and 3) two types of semantic consistency (verb-purpose and verb-place agreements), respectively, and their general listening proficiency was examined using standardized tests. A number of findings have been made about the interactive relationships between the three types of auditory error recognition and general listening proficiency. Analyses based on the OPLS (Orthogonal Projections to Latent Structure) regression model have disclosed, for example, that the three types of auditory error recognition are linked in a non-linear way: the highest explanatory power for general listening proficiency may be attained when quadratic interactions between auditory recognition of errors related to vowel minimal pair words and that of errors related to noun phrase-based word order are embraced (R2=.33, p=.01).

Keywords: auditory error recognition, intensive listening, interaction, investigation

Procedia PDF Downloads 492
867 Annotation Ontology for Semantic Web Development

Authors: Hadeel Al Obaidy, Amani Al Heela

Abstract:

The main purpose of this paper is to examine the concept of semantic web and the role that ontology and semantic annotation plays in the development of semantic web services. The paper focuses on semantic web infrastructure illustrating how ontology and annotation work to provide the learning capabilities for building content semantically. To improve productivity and quality of software, the paper applies approaches, notations and techniques offered by software engineering. It proposes a conceptual model to develop semantic web services for the infrastructure of web information retrieval system of digital libraries. The developed system uses ontology and annotation to build a knowledge based system to define and link the meaning of a web content to retrieve information for users’ queries. The results are more relevant through keywords and ontology rule expansion that will be more accurate to satisfy the requested information. The level of results accuracy would be enhanced since the query semantically analyzed work with the conceptual architecture of the proposed system.

Keywords: semantic web services, software engineering, semantic library, knowledge representation, ontology

Procedia PDF Downloads 156
866 Secure Bio Semantic Computing Scheme

Authors: Hiroshi Yamaguchi, Phillip C. Y. Sheu, Ryo Fujita, Shigeo Tsujii

Abstract:

In this paper, the secure BioSemantic Scheme is presented to bridge biological/biomedical research problems and computational solutions via semantic computing. Due to the diversity of problems in various research fields, the semantic capability description language (SCDL) plays and important role as a common language and generic form for problem formalization. SCDL is expected the essential for future semantic and logical computing in Biosemantic field. We show several example to Biomedical problems in this paper. Moreover, in the coming age of cloud computing, the security problem is considered to be crucial issue and we presented a practical scheme to cope with this problem.

Keywords: biomedical applications, private information retrieval (PIR), semantic capability description language (SCDL), semantic computing

Procedia PDF Downloads 373
865 Variational Explanation Generator: Generating Explanation for Natural Language Inference Using Variational Auto-Encoder

Authors: Zhen Cheng, Xinyu Dai, Shujian Huang, Jiajun Chen

Abstract:

Recently, explanatory natural language inference has attracted much attention for the interpretability of logic relationship prediction, which is also known as explanation generation for Natural Language Inference (NLI). Existing explanation generators based on discriminative Encoder-Decoder architecture have achieved noticeable results. However, we find that these discriminative generators usually generate explanations with correct evidence but incorrect logic semantic. It is due to that logic information is implicitly encoded in the premise-hypothesis pairs and difficult to model. Actually, logic information identically exists between premise-hypothesis pair and explanation. And it is easy to extract logic information that is explicitly contained in the target explanation. Hence we assume that there exists a latent space of logic information while generating explanations. Specifically, we propose a generative model called Variational Explanation Generator (VariationalEG) with a latent variable to model this space. Training with the guide of explicit logic information in target explanations, latent variable in VariationalEG could capture the implicit logic information in premise-hypothesis pairs effectively. Additionally, to tackle the problem of posterior collapse while training VariaztionalEG, we propose a simple yet effective approach called Logic Supervision on the latent variable to force it to encode logic information. Experiments on explanation generation benchmark—explanation-Stanford Natural Language Inference (e-SNLI) demonstrate that the proposed VariationalEG achieves significant improvement compared to previous studies and yields a state-of-the-art result. Furthermore, we perform the analysis of generated explanations to demonstrate the effect of the latent variable.

Keywords: natural language inference, explanation generation, variational auto-encoder, generative model

Procedia PDF Downloads 126
864 Mondoc: Informal Lightweight Ontology for Faceted Semantic Classification of Hypernymy

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 103
863 Investigating the Concept of Joy in Modern English Fiction

Authors: Zarine Avetisyan

Abstract:

The paradigm of Modern Linguistics incorporates disciplines which allow to analyze both language and discourse units and to demonstrate the multi-layeredness of lingo-cultural consciousness. By implementing lingo-cognitive approach to discourse and communication studies, the present paper tries to create the integral linguistic picture of the concept of joy and to analyze the lexico-semantic groups and relevant lexico-semantic variants of its realization in the context of Modern English fiction.

Keywords: concept of joy, lexico-semantic variant, semantic sign, cognition

Procedia PDF Downloads 260
862 Web 2.0 Enabling Knowledge-Sharing Practices among Students of IIUM: An Exploration of the Determinants

Authors: Shuaibu Hassan Usman, Ishaq Oyebisi Oyefolahan

Abstract:

This study was aimed to explore the latent factors in the web 2.0 enabled knowledge sharing practices instrument. Seven latent factors were identified through a factor analysis with orthogonal rotation and interpreted based on simple structure convergence, item loadings, and analytical statistics. The number of factors retains was based on the analysis of Kaiser Normalization criteria and Scree plot. The reliability tests revealed a satisfactory reliability scores on each of the seven latent factors of the web 2.0 enabled knowledge sharing practices. Limitation, conclusion, and future work of this study were also discussed.

Keywords: factor analysis, latent factors, knowledge sharing practices, students, web 2.0 enabled

Procedia PDF Downloads 413
861 Graph Planning Based Composition for Adaptable Semantic Web Services

Authors: Rihab Ben Lamine, Raoudha Ben Jemaa, Ikram Amous Ben Amor

Abstract:

This paper proposes a graph planning technique for semantic adaptable Web Services composition. First, we use an ontology based context model for extending Web Services descriptions with information about the most suitable context for its use. Then, we transform the composition problem into a semantic context aware graph planning problem to build the optimal service composition based on user's context. The construction of the planning graph is based on semantic context aware Web Service discovery that allows for each step to add most suitable Web Services in terms of semantic compatibility between the services parameters and their context similarity with the user's context. In the backward search step, semantic and contextual similarity scores are used to find best composed Web Services list. Finally, in the ranking step, a score is calculated for each best solution and a set of ranked solutions is returned to the user.

Keywords: semantic web service, web service composition, adaptation, context, graph planning

Procedia PDF Downloads 495
860 Towards a Large Scale Deep Semantically Analyzed Corpus for Arabic: Annotation and Evaluation

Authors: S. Alansary, M. Nagi

Abstract:

This paper presents an approach of conducting semantic annotation of Arabic corpus using the Universal Networking Language (UNL) framework. UNL is intended to be a promising strategy for providing a large collection of semantically annotated texts with formal, deep semantics rather than shallow. The result would constitute a semantic resource (semantic graphs) that is editable and that integrates various phenomena, including predicate-argument structure, scope, tense, thematic roles and rhetorical relations, into a single semantic formalism for knowledge representation. The paper will also present the Interactive Analysis​ tool for automatic semantic annotation (IAN). In addition, the cornerstone of the proposed methodology which are the disambiguation and transformation rules, will be presented. Semantic annotation using UNL has been applied to a corpus of 20,000 Arabic sentences representing the most frequent structures in the Arabic Wikipedia. The representation, at different linguistic levels was illustrated starting from the morphological level passing through the syntactic level till the semantic representation is reached. The output has been evaluated using the F-measure. It is 90% accurate. This demonstrates how powerful the formal environment is, as it enables intelligent text processing and search.

Keywords: semantic analysis, semantic annotation, Arabic, universal networking language

Procedia PDF Downloads 566