• Journal of the Korea Society of Computer and Information
• /
• v.22 no.4
• /
• pp.41-49
• /
• 2017

Word sense disambiguation(WSD) that determines the exact meaning of homonym which can be used in different meanings even in one form is very important to understand the semantical meaning of text document. Many recent researches on WSD have widely used NNLM(Neural Network Language Model) in which neural network is used to represent a document into vectors and to analyze its semantics. Among the previous WSD researches using NNLM, RNN(Recurrent Neural Network) model has better performance than other models because RNN model can reflect the occurrence order of words in addition to the word appearance information in a document. However, since RNN model uses only the forward order of word occurrences in a document, it is not able to reflect natural language's characteristics that later words can affect the meanings of the preceding words. In this paper, we propose a WSD scheme using Bidirectional RNN that can reflect not only the forward order but also the backward order of word occurrences in a document. From the experiments, the accuracy of the proposed model is higher than that of previous method using RNN. Hence, it is confirmed that bidirectional order information of word occurrences is useful for WSD in Korean language.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2002.02a
• /
• pp.249-258
• /
• 2002

We propose an algorithm for the automatic acquisition of a bilingual lexicon in the legal domain. We make use of a parallel corpus of bilingual court judgments, aligned to the sentence level, and analyse the bilingual context profiles to extract corresponding legal terms in both languages. Our method is different from those in past studies as it does not require any prior knowledge source, and naturally extends to multi-word terms in either language. A pilot test was done with a sample of ten legal terms, each with ten or more occurrences in the data. Encouraging results of about 75% average accuracy were obtained. This figure does not only reflect the effectiveness of the method for bilingual lexicon acquisition, but also its potential for bilingual alignment at the word or expression level.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.11 no.4
• /
• pp.238-246
• /
• 2011

This paper proposes a new semantic representation and its associated similarity measure. The representation expresses textual context observed in a context of a certain term as a network where nodes are terms and edges are the number of cooccurrences between connected terms. To compare terms represented in networks, a graph kernel is adopted as a similarity measure. The proposed representation has two notable merits compared with previous semantic representations. First, it can process polysemous words in a better way than a vector representation. A network of a polysemous term is regarded as a combination of sub-networks that represent senses and the appropriate sub-network is identified by context before compared by the kernel. Second, the representation permits not only words but also senses or contexts to be represented directly from corresponding set of terms. The validity of the representation and its similarity measure is evaluated with two tasks: synonym test and unsupervised word sense disambiguation. The method performed well and could compete with the state-of-the-art unsupervised methods.

• Korea Journal of Hospital Management
• /
• v.14 no.4
• /
• pp.25-51
• /
• 2009

This model was empirically developed to test the effect of medical service quality and hospital's reputation on customer satisfaction, repurchase intention, and negative word of mouth as to disease severity. The model was tested in the context of the hospital industry. The findings are as follows. First, medical service provider's functional quality and technical service quality have significant effect on customer satisfaction. Second, hospital's reputation has positive(+) effect on customer satisfaction and significant negative effect on negative word of mouth. Third, customer satisfaction with medical service quality has significantly positive effect on customer's repurchase intention and has negative(-) effect on customer's negative word of mouth. Furthermore, customer's negative word of mouth has negative effect on their repurchase intention. Fourth, as to different disease severity, medical service quality and hospital's reputation have different effect on customer satisfaction, repurchase intention, and negative word of mouth. When patients get slightly ill, functional service quality and technical service quality have direct influence on customer satisfaction which has positive influence on repurchase intention and negative influence on negative word of mouth. Finally, negative word of mouth has negative effect on customer's repurchase intention. However, while hospital's reputation doesn't have effect on customer satisfaction, the reputation has significantly negative effect on negative word of mouth. When patients get seriously ill, only functional service quality has positive effect on customer satisfaction which influences on customer's repurchase intention and negatively influences on negative word of mouth. On the contrary, negative word of mouth doesn't influence on customer's repurchase intention as patients want to treat serious diseases in the large general hospitals even though negative word of mouth is known to them.

• Knowledge Management Research
• /
• v.14 no.1
• /
• pp.1-19
• /
• 2013

Consumers have collected information and sought advices from other consumer through Internet. They could collect information in virtual space (online) not real world, that is Electronic Word of Mouth (eWOM). This study focused on research the factors on effect in Electronic Word-of-Mouth (eWOM) in the open market which is mediate between individuals and online stores. This is an exploratory study for research on finding factors of effect in eWOM. First of all, 5factors are selected from interview with 31 consumers. Then online surveys are conducted and 5 factors are significantly supported. This study is academically new approach on an exploratory study and it could suggest marketers to strategically manage eWOM.

• Journal of Contemporary Eastern Asia
• /
• v.13 no.2
• /
• pp.3-14
• /
• 2014

Online communities are an important source of electronic-word-of-mouth (eWOM), however few studies have examined these types of messages within the Middle Eastern context. This study focuses on Kuwaiti women as members of an online beauty forum; previous work has suggested a mediating effect of gender with women being more likely to trust and follow-up word-of-mouth with a purchase. A conceptual model, based on existing theoretical contributions, provides the basis of a coding framework for the message characteristics that influence members' eWOM adoption. A sub-set of the analysis is presented: 218 threads (1820 messages, coded into 6702 units) illustrating cases where eWOM was adopted and thereby demonstrating continuance intention with members returning to the forum. Content analysis revealed the prevalence of emotional aspects in messages, coded into a new category of 'community bonding'. Findings show that emotion expressed in messages is as influential and important as cognitive aspects of argument quality.

• Journal of Educational Research in Mathematics
• /
• v.12 no.1
• /
• pp.17-27
• /
• 2002

To solve the addition word problems provides young children the chance to learn about and exercise in problem solving. This paper focuses on two aspects to be considered in addition word problems: the homogeneity of objects and the variety of contexts. The homogeneity of objects involved in addition word problems has to be kept in the following reasons: concept of unit, effectiveness of information, prevention of inappropriate variety, inconsistency of mathematics with real world, continuity between elementary and secondary mathematics. And for the variety of contexts, the additive structure proposed by G. Vergnaud, can be considered: composition, transformation, relation of comparison, composition of two transformations, composition of two relations, transformation of a relation. According to this structure, some examples, which contain homogeneous objects, were extracted from the elementary school mathematics textbooks.

• English Language & Literature Teaching
• /
• v.15 no.2
• /
• pp.51-70
• /
• 2009

This study focuses on the asymmetrical realization of homorganic nasal-obstruent stop clusters in English when they occur word medially and word finally. This uneven realization of NC clusters is not only controlled by the place of articulation of the cluster constituents but also by the agreement of voicing feature specifications of the cluster elements. We propose context-sensitive constraints, which are more specified versions than *NC (Pater, 1996, 1999, 2004). The result of the study reveals that homorganic NC clusters consisting of coronal place feature are faithfully realized word finally while they are constrained word medially. The deletion of voiceless post-nasal coronal stop should be considered a new language specific strategy to avoid *NC.

• Journal of KIISE
• /
• v.41 no.12
• /
• pp.1081-1089
• /
• 2014

Context-sensitive spelling-error correction methods are largely classified into rule-based methods and statistical data-based methods, the latter of which is often preferred in research. Statistical error correction methods consider context-sensitive spelling error problems as word-sense disambiguation problems. The method divides a vocabulary pair, for correction, which consists of a correction target vocabulary and a replacement candidate vocabulary, according to the context. The present paper proposes a method that integrates a word-phrase n-gram model into a conventional model in order to improve the performance of the probability model by using a correction vocabulary pair, which was a result of a previous study performed by this research team. The integrated model suggested in this paper includes a method used to interpolate the probability of a sentence calculated through each model and a method used to apply the models, when both methods are sequentially applied. Both aforementioned types of integrated models exhibit relatively high accuracy and reproducibility when compared to conventional models or to a model that uses only an n-gram.

• Journal of KIISE:Databases
• /
• v.36 no.4
• /
• pp.254-262
• /
• 2009

As the trend of e-business activities develop, customers come into contact with products through on-line shopping sites and lots of customers refer product reviews before the purchasing on-line. However, as the volume of product reviews grow, it takes a great deal of time and effort for customers to read and evaluate voluminous product reviews. Lately, attention is being paid to Opinion Mining(OM) as one of the effective solutions to this problem. In this paper, we propose an efficient method for opinion sentiment classification of product reviews using product specific context information of words occurred in the reviews. We define the context information of words and propose the application of context for sentiment classification and we show the performance of our method through the experiments. Additionally, in case of word corpus construction, we propose the method to construct word corpus automatically using the review texts and review scores in order to prevent traditional manual process. In consequence, we can easily get exact sentiment polarities of opinion words in product reviews.