• KIISE Transactions on Computing Practices
• /
• v.22 no.1
• /
• pp.50-55
• /
• 2016

To attain an understanding of customers' opinions or demands regarding a companies' products or service, it is important to consider VOC (Voice of Customer) data; however, it is difficult to understand contexts from VOC because segmented and duplicate sentences and a variety of dialog contexts. In this article, POS (part of speech) and morphemes were selected as language resources due to their semantic importance regarding documents, and based on these, we defined an LSP (Lexico-Semantic-Pattern) to understand the structure and semantics of the sentences and extracted summary by key sentences; furthermore the LSP was introduced to connect the segmented sentences and remove any contextual repetition. We also defined the LSP by categories and classified the documents based on those categories that comprise the main sentences matched by LSP. In the experiment, we classified the VOC-data documents for the creation of a summarization before comparing the result with the previous methodologies.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.345-352
• /
• 2006

The practical English-Korean machine translation system should be able to translate long sentences quickly and accurately. The intra-sentence segmentation method has been proposed and contributed to speeding up the syntactic analysis. This paper proposes the syntactic category prediction method using decision trees for getting accurate parsing results. In parsing with segmentation, the segment is separately parsed and combined to generate the sentence structure. The syntactic category prediction would facilitate to select more accurate analysis structures after the partial parsing. Thus, we could improve the parsing accuracy by the prediction. We construct features for predicting syntactic categories from the parsed corpus of Wall Street Journal and generate decision trees. In the experiments, we show the performance comparisons with the predictions by human-built rules, trigram probability and neural networks. Also, we present how much the category prediction would contribute to improving the translation quality.

• Korean Journal of Cognitive Science
• /
• v.19 no.2
• /
• pp.205-222
• /
• 2008

This study investigated scope relations between quantifier and focus which are represented in quantified sentences. In the sentence which has both strong quantifier and weak quantifier, one of them has a wide scope and a presuppositional reading, and the other which has a narrow one is interpreted non-presuppositionally. In Korean, when a weak quantifier is separated from VP in surface representation, whether it is a subject or an object, it has only a presuppositional reading. Therefore, there is no scope ambiguity in that sentence. However, when weak quantifier which is an object of transitive verb or a subject of transitive verb is sensitive to focus, it is available to non-presuppositional reading, so that the sentence seems to be ambiguous. Once even weak quantifier out of VP in the Surface structure is focused, it becomes to be in the scope of focus (focal phrase) which is formed in Logical form by a focus projection. And this scope of focus corresponds to a nuclear scope. That is to say, focus operates on the weak quantifier to be interpreted non-presuppositionally in a nuclear scope.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.662-667
• /
• 2022

Semantic role labeling task(SRL) is to extract predicate and arguments such as agent, patient, place, time. In the previously SRL task studies, a pipeline method extracting linguistic features of sentence has been proposed, but in this method, errors of each extraction work in the pipeline affect semantic role labeling performance. Therefore, methods using End-to-End neural network model have recently been proposed. In this paper, we propose a neural network model using the Biaffine Average Attention model for SRL task. The proposed model consists of a structure that can focus on the entire sentence information regardless of the distance between the predicate in the sentence and the arguments, instead of LSTM model that uses the surrounding information for prediction of a specific token proposed in the previous studies. For evaluation, we used F1 scores to compare two models based BERT model that proposed in existing studies using F1 scores, and found that 76.21% performance was higher than comparison models.

• Language and Information
• /
• v.17 no.2
• /
• pp.67-91
• /
• 2013

This paper describes Korean Nominal Bank, a project that provides argument structure for instances of the predicative nouns in the Sejong parsed Corpus. We use the language resources of the Sejong project, so that the same set of data is annotated with more and more levels of annotation, since a new type of a language resource building project could bring new information of separate and isolated processing. We have based on the annotation scheme based on the Sejong electronic dictionary, semantically tagged corpus, and syntactically analyzed corpus. Our work also involves the deep linguistic knowledge of syntaxsemantic interface in general. We consider the semantic theories including the Frame Semantics of Fillmore (1976), argument structure of Grimshaw (1990) and argument alternation of Levin (1993), and Levin and Rappaport Hovav (2005). Various syntactic theories should be needed in explaining various sentence types, including empty categories, raising, left (or right dislocation). We also need an explanation on the idiosyncratic lexical feature, such as collocation and etc.

• Journal of the Korean Home Economics Association
• /
• v.39 no.7
• /
• pp.71-84
• /
• 2001

The purpose of this study was to investigate the development of preschoolers'narrative competence. The subject were 60 preschoolers aged 3 through 5 years who were enrolled in the day care center All the subjects were asked to produce a new story. All the story children toad were recorded on audiotape. The data were analyzed Qualitatively and quantitatively using content analysis and the statistical package for Social Science 9.0. The main results of this study were as follows. 1) Significant age difference was observed in preschooler's narrative structure. Older children produced structurally more complex stories containing setting, character, initiating event, attempt and consequence than younger children. 2) Significant age difference was observed in preschooler's narrative length. Older children used significantly more words and sentence when they produced stories than younger children.3) Preschooler'narrative structure was significantly correlated with narrative length.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.4E
• /
• pp.26-30
• /
• 1999

This paper introduces a prosodic phrasing method in Korean to improve the naturalness of speech synthesis, especially in text-to-speech conversion. In prosodic phrasing, it is necessary to understand the structure of a sentence through a language processing procedure, such as part-of-speech (POS) tagging and parsing, since syntactic structure correlates better with the prosodic structure of speech than with other factors. In this paper, the prosodic phrasing procedure is treated from two perspectives: dependency parsing and prosodic phrasing using dependency relations. This is appropriate for Ural-Altaic, since a prosodic boundary in speech usually concurs with a governor of dependency relation. From experimental results, using the proposed method achieved 12% improvement in prosody boundary prediction accuracy with a speech corpus consisting 300 sentences uttered by 3 speakers.

• Phonetics and Speech Sciences
• /
• v.8 no.4
• /
• pp.71-78
• /
• 2016

The purpose of this study is to investigate the effect of Japanese(L1) on the production of Korean accentual phrases(L2). Korean and Japanese have a similar prosodic structure. But different from Korean, Japanese is a pitch accent language. So each word has its own pitch accent. And pitch accents are maintained in the sentence intonation. This difference will have a negative influence on the production of Korean sentence intonation. For this study 4 Korean natives speakers and 10 advanced Japanese learners of Korean participated in the production test. The material analysed constituted 11 Korean sentences, six of which contain formally identical Sino-Korean and Sino-Japanese words. The results show that the initial pitch pattern of Korean accentual phrases was affected by Japanese pitch accent types and this interference was greater for formally identical Sino-Korean and Sino-Japanese words. But besides initial tones of accentual phrase, some positive interference was observed in the internal tonal pattern of accentual phrase. In the phonetic realization, the internal pitch range and initial pitch rising of accentual phrases was greater for Japanese learners of Korean than native speakers of Korean.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.673-675
• /
• 2005

The art psychotherapy expert system is a computer system which helps to analyse one's psychology through pictures. However we need a standard criterion because the psychology, the target of the art psychotherapy, does not only have a ambiguous criterion but also a vast range. We're going to suggest a criterion in the field of the art psychotherapy by constructing systematic database through knowledge acquirement of the art psychotherapy expert system. In this study we introduce a system which enables systematic classification and confirmation of symptoms according to mental analyses. The suggested system enables confirmation of a classical structure and systematic classification of knowledges through conversation by extracting nouns through sentence analysis from the knowledge of descriptive form based on the clinical purpose of sentence analysis.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.4958-4970
• /
• 2019

As technology advances, the amount of fake news is increasing more and more by various reasons such as political issues and advertisement exaggeration. However, there have been very few research works on fake news detection, especially which uses grammatical transformation on deep neural network. In this paper, we shall present a new Fake News Detection Model, called FAGON(Fake news detection model using Grammatical transformation On deep Neural network) which determines efficiently if the proposition is true or not for the given article by learning grammatical transformation on neural network. Especially, our model focuses the Korean language. It consists of two modules: sentence generator and classification. The former generates multiple sentences which have the same meaning as the proposition, but with different grammar by training the grammatical transformation. The latter classifies the proposition as true or false by training with vectors generated from each sentence of the article and the multiple sentences obtained from the former model respectively. We shall show that our model is designed to detect fake news effectively by exploiting various grammatical transformation and proper classification structure.