• Journal of Information Science Theory and Practice
• /
• v.7 no.3
• /
• pp.21-30
• /
• 2019

Information about the formation and filling (in 2014 to 2016) of a terminological dictionary on electronics and radioengineering and collective work (in 2017 to 2018) with a data bank "TERMIN" is presented in this article. In purpose of creating an instrument of navigating the modern scientific-technical space a net of terms with set semantic links is described. This set is based on the analysis of terms' definitions (each term is checked for inclusion in the definitions of all other terms; the definitions were borrowed from reputable reference editions: encyclopedias, dictionaries, reference books). The created model of a system that consists of different information sources, in which it (information) is indexed by the terminology of Russian State Rubricator of Scientific and Technical Information rubrics and/or keywords, is described. There is an access for the search in all these sources in the system. Searching inquiries are referred to in the language of these rubrics or formulated by arbitrary terms. The system is to refer to information sources and give out relevant information. In accordance with this model, semantic links of various types, which allow expanding a search at different modalities of query, should be set among data bank terms. Obtained links will have to increase semantic matching, i.e., they can provide actual understanding of the meaning of the information that is being sought.

• Journal of KIISE:Software and Applications
• /
• v.37 no.4
• /
• pp.317-322
• /
• 2010

This paper proposes how to improve performance of the Korean document sentiment-classification system using semantic properties of the sentiment words. A sentiment word means a word with sentiment, and sentiment features are defined by a set of the sentiment words which are important lexical resource for the sentiment classification. Sentiment feature represents different sentiment intensity in general field and in specific domain. In general field, we can estimate the sentiment intensity using a snippet from a search engine, while in specific domain, training data can be used for this estimation. When the sentiment intensity of the sentiment features are estimated, it is called semantic orientation and is used to estimate the sentiment intensity of the sentences in the text documents. After estimating sentiment intensity of the sentences, we apply that to the weights of sentiment features. In this paper, we evaluate our system in three different cases such as general, domain-specific, and general/domain-specific semantic orientation using support vector machine. Our experimental results show the improved performance in all cases, and, especially in general/domain-specific semantic orientation, our proposed method performs 3.1% better than a baseline system indexed by only content words.

• ETRI Journal
• /
• v.32 no.3
• /
• pp.482-485
• /
• 2010

Feature selection is very important for feature-based relation classification tasks. While most of the existing works on feature selection rely on linguistic information acquired using parsers, this letter proposes new features, including probabilistic and semantic relatedness features, to manifest the relatedness between patterns and certain relation types in an explicit way. The impact of each feature set is evaluated using both a chi-square estimator and a performance evaluation. The experiments show that the impact of relatedness features is superior to existing well-known linguistic features, and the contribution of relatedness features cannot be substituted using other normally used linguistic feature sets.

• The KIPS Transactions:PartD
• /
• v.12D no.5 s.101
• /
• pp.789-796
• /
• 2005

Because existing information retrieval systems, in particular library retrieval systems, use 'exact keyword matching' with user's query, they present user with massive results including irrelevant information. So, a user spends extra effort and time to get the relevant information from the results. Thus, this paper will propose SULRM a Retrieval Model using Subject Classification Table, User profile, and LSI(Latent Semantic Indexing), to provide more relevant results. SULRM uses document filtering technique for classified data and document ranking technique for non-classified data in the results of keyword-based retrieval. Filtering technique uses Subject Classification Table, and ranking technique uses user profile and LSI. And, we have performed experiments on the performance of filtering technique, user profile updating method, and document ranking technique using the results of information retrieval system of our university' digital library system. In case that many documents are retrieved proposed techniques are able to provide user with filtered data and ranked data according to user's subject and preference.

• Korean Journal of Child Studies
• /
• v.18 no.2
• /
• pp.73-85
• /
• 1997

The purpose of the present study was to examine the role of semantic and syntactic knowledge in the first language acquisition of Korean classifiers. The elicited classifiers production test(EPT) was conducted to 105 children aged from 2 to 7. EPT consisted of 16 classifiers and two items for each classifier. 32 items were divided into 2 major semantic features: animacy and inanimacy. The semantic features of inanimacy were subcategorized into 3 features such as neutral, shape and function. The results revealed that; 1) children produced the correct structure of classification from the very early age with correct word order of the noun phrase showing early fundamental syntactic knowledge; 2) The earliest response pattern was to respond to all nouns in the same way using a neutral classifier showing no apparent semantic basis for their choice; 3) Children didn't show any preference for animate, shape, or function classifiers.

• Journal of Korea Multimedia Society
• /
• v.24 no.1
• /
• pp.1-12
• /
• 2021

In this paper, we present a new architecture for semantic segmentation. Semantic segmentation aims at a pixel-wise classification which is important to fully understand images. Previous semantic segmentation networks use features of multi-layers in the encoder to predict final results. However, they do not contain various receptive fields in the multi-layers features, which easily lead to inaccurate results for boundaries between different classes and small objects. To solve this problem, we propose a multi-path feature fusion module that allows for features of each layers to contain various receptive fields by use of a set of dilated convolutions with different dilatation rates. Various experiments demonstrate that our method outperforms previous methods in terms of mean intersection over unit (mIoU).

• The KIPS Transactions:PartD
• /
• v.12D no.1 s.97
• /
• pp.165-178
• /
• 2005

A product classification scheme is the foundation on which product databases are designed, and plays a central role in almost all aspects of management and use of product information. It needs to meet diverse user views to support efficient and convenient use of product information. It needs to be changed and evolved very often without breaking consistency in the cases of introduction of new products, extinction of existing products, class reorganization, and class specialization. It also needs to be merged and mapped with other classification schemes without information loss when B2B transactions occur. For these requirements, a classification scheme should be so dynamic that it takes in them within right time and cost. The existing classification schemes widely used today such as UNSPSC and eCl@ss, however, have a lot of limitations to meet these requirements for dynamic features of classification. Product information implies a plenty of semantics such as class attributes like material, time, place, etc., and integrity constraints. In this Paper, we analyze the dynamic features of product databases and the limitation of existing code based classification schemes, and describe the semantic classification model proposed in [1], which satisfies the requirements for dynamic features of product databases. It provides a means to explicitly and formally express more semantics for product classes and organizes class relationships into a graph.

• Language and Information
• /
• v.9 no.1
• /
• pp.1-18
• /
• 2005

In Korean terminologies, adjectival terms are rare, and the meaning and function associated with adjectives in Indo-European languages are often realized instead in noun form. However, the rarer adjectival terms we, the more they are used in restrictive and repetitive ways in specialized domains. Thus, it is important to distinguish the different senses of these terms. In this work, focusing on semantic modeling in terminology, we distinguish the different senses of adjectival medical terms by applying lexico-semantic criteria (L'Homme, 2004a) and by classifying the semantic category of the arguments of the adjective (Bae and others, 2002). The result not only contributes to enriching medical terminology, but also empirically demonstrates a method for distinguishing the different senses of adjectival medical terms. In this work, we obtained an average of 1.854 senses for each term. We used the KAIST corpus, composed of medical texts (1,500,000 eojeols), and a group of texts on various subjects (40,000,000 eojeols)

• Database Research
• /
• v.34 no.3
• /
• pp.3-13
• /
• 2018

Text classification is one of the text mining technologies that classifies a given textual document into its appropriate categories and is used in various fields such as spam email detection, news classification, question answering, emotional analysis, and chat bot. In general, the text classification system utilizes machine learning algorithms, and among a number of algorithms, naïve Bayes and support vector machine, which are suitable for text data, are known to have reasonable performance. Recently, with the development of deep learning technology, several researches on applying deep neural networks such as recurrent neural networks (RNN) and convolutional neural networks (CNN) have been introduced to improve the performance of text classification system. However, the current text classification techniques have not yet reached the perfect level of text classification. This paper focuses on the fact that the text data is expressed as a vector only with the word dimensions, which impairs the semantic information inherent in the text, and proposes a neural network architecture based upon the semantic tensor space model.

• Journal of KIISE:Databases
• /
• v.33 no.1
• /
• pp.102-116
• /
• 2006

Electronic catalogs (or e-catalogs) hold information about the goods and services offered or requested by the participants, and consequently, form the basis of an e-commerce transaction. Catalog management is complicated by a number of factors and product classification is at the core of these issues. Classification hierarchy is used for spend analysis, custom3 regulation, and product identification. Classification is the foundation on which product databases are designed, and plays a central role in almost all aspects of management and use of product information. However, product classification has received little formal treatment in terms of underlying model, operations, and semantics. We believe that the lack of a logical model for classification Introduces a number of problems not only for the classification itself but also for the product database in general. It needs to meet diverse user views to support efficient and convenient use of product information. It needs to be changed and evolved very often without breaking consistency in the cases of introduction of new products, extinction of existing products, class reorganization, and class specialization. It also needs to be merged and mapped with other classification schemes without information loss when B2B transactions occur. For these requirements, a classification scheme should be so dynamic that it takes in them within right time and cost. The existing classification schemes widely used today such as UNSPSC and eClass, however, have a lot of limitations to meet these requirements for dynamic features of classification. In this paper, we try to understand what it means to classify products and present how best to represent classification schemes so as to capture the semantics behind the classifications and facilitate mappings between them. Product information implies a plenty of semantics such as class attributes like material, time, place, etc., and integrity constraints. In this paper, we analyze the dynamic features of product databases and the limitation of existing code based classification schemes. And describe the semantic classification model, which satisfies the requirements for dynamic features oi product databases. It provides a means to explicitly and formally express more semantics for product classes and organizes class relationships into a graph. We believe the model proposed in this paper satisfies the requirements and challenges that have been raised by previous works.