• The KIPS Transactions:PartB
• /
• v.10B no.1
• /
• pp.41-46
• /
• 2003

This thesis composes separated words in text for extracting keywords from Japanese, proposes extracting indexing keywords which consist of a compound noun using words and sentences information with the rules in the sentences. It constructs generative rules of compound nouns to be based In dependence as a result of analysing character of keywords in the text not the same way as before. To hold other extracting keywords and the content of sentence, and suggest how to decide importance concerned some restriction and repetition of words about generative rules. To verify the validity of keywords extracting, we have used titles and abstracts from Japanese thesis 65 files about natural language and/or voice processing, and obtain 63% in outputting one in the top rank.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1919-1925
• /
• 2022

In this paper, we propose an image-to-image translation approach based on the conditional generative adversarial network for semantic segmentation. Semantic segmentation is the task of clustering parts of an image together which belong to the same object class. Unlike the traditional pixel-wise classification approach, the proposed method parses an input RGB image to its corresponding semantic segmentation mask using a pixel regression approach. The proposed method is based on the Pix2Pix image synthesis method. We employ residual connections-based convolutional neural network architectures for both the generator and discriminator architectures, as the residual connections speed up the training process and generate more accurate results. The proposed method has been trained and tested on the NYU-depthV2 dataset and could achieve a good mIOU value (49.5%). We also compare the proposed approach to the current methods in semantic segmentation showing that the proposed method outperforms most of those methods.

• Sijohaknonchong
• /
• v.21
• /
• pp.143-164
• /
• 2004

The purpose of this study is to clarify that 'Kanghosasiga' is the Ynsijo which has general unification of the content and having general unification is based. on the using one definite frame. although 'Kanghosasiga' used different subject matters that have characteristics of four season in forming one theme. The definite frame is divided into two frames, inner frame and outer frame. Outer frame is common in four works, and it represents the place in which the speaker lives(강호), speaker (이몸), relationship between speaker and the king(군은), the condition of 'kangho' and speaker. And in this paper, the generative condition of phrases is so analyzed that the compression and the simplicity of expression are explained, and the purpose of generative phrases is so analyzed that satisfaction at life is represented. It is considered if it is possible to extended to '태평성대(the happy era)' in the social view. Inner frame is the detail structure of content of the work. Each of the first, second, third of the verses of four works have common structure. After analyzing each content, the characteristic of 'Kanghosasiga' was explained. The first of verses of 'Kanghosasiga' represent gusto of the four season. The second is constructed with 'the clause that functions as instruction' because 'speaker' that is the words that functions as index, and represents in detail gusto of the first. The third is connotative expression connected with the second. The third implies purpose that the writer try to gain private living with formal viewpoint. The structure of the inner frame of 'Kanghosasiga' shows a process; 'introducing season' $\to$ 'gusto about season' $\to$ 'enjoying with season' $\to$ 'peace in mind'. The first of verses of 'Kanghosasiga' is the clue of the second. The second is the reaction of the first. The third has character as estimation of the forepart. The structure of the outer frame can be shown if the structure of the inner frame has '감군은‘(being grateful to king's grace). ultimate purpose of the writer is to praise king's administration.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.1
• /
• pp.381-388
• /
• 2020

This paper discusses English Hedges or Hedging Expressions on the basis of their morphosyntactic-pragramatic properties within the perspective of sociolinguistics. The term, 'Hedges' for the past decades since Lakoff(1973), has received little attention from the English grammar circles such as morphosyntax and the generative grammar theories. This paper presents a more comprehensive approach to the identification, distributions, functions, and the morphosyntactic properties of English Hedges. The earlier research on English Hedges in the 70's show that hedges are metalinguistic or mitadiscourse expressions which constitute a means for executing Politeness strategy in pragmatics. Nonetheless, research from the interface of syntactic-pragmatics has been scarce. This article suggests a more complex body of English hedges that have not been extensively discussed in the literature. Additionally, their configurational domain is to be proposed as part of the PolP with [±hedged] above CP⁺ (or CP beyond). The ramifications of the current study are suggested in terms of comparative linguistics, EFL/ESL studies of English for global communication, and pragmatics-sensitive machine translation studies in the forseeable future.