• Journal of KIISE:Software and Applications
• /
• v.27 no.3
• /
• pp.302-313
• /
• 2000

In English-Korean machine translation, transitive verb-objective collocation is utilized for accurate translation of an English verbal phrase into Korean. This paper presents an algorithm for correct verb translation based on the k-nearest neighbor learning. The semantic distance is defined on the WordNet for the k-nearest neighbor learning. And we also present algorithms for automatic collocation dictionary optimization. The algorithms extract transitive verb-objective pairs as training examples from large corpora and minimize the examples, considering the tradeoff between translation accuracy and example size. Experiments show that these algorithms optimized collocation dictionary keeping about 90% accuracy for a verb 'build'.

• Korean Linguistics
• /
• v.48
• /
• pp.333-354
• /
• 2010

When defining the word related to passive and causative in Korean dictionary, the meaning of headword can be explained by linking them to other related words. The link could be expressed into two forms; the one is 'passive verb causative verb of A' and the other is 'passive form causative form of A.' Whichever the dictionary takes, the important thing is that the content to which it refer should be correct. However the format of 'passive verb causative verb of A' and 'passive form causative form of A' is problematic because the definition of headword does not contain semantic information but syntactic or morphological information. Generic concept 'passive form causative form' and 'passive verb causative verb' refers to respectively morphological and syntactic level but specific concept 'A' refers to semantic level. These morphological, syntactic and semantic level can not be a same dimension so the size of their denotation can not be compared. The way of transform syntactic dimension 'passive verb causative verb' and morphological dimension 'passive form causative form' into semantic dimension is removing 'verb' and 'form' from 'passive verb causative verb' and 'passive form causative form' respectively. Therefore the expression 'passive verb causative verb of A' or 'passive form causative form of A' ought be changed into 'passive causative of A.'

• Genomics & Informatics
• /
• v.18 no.2
• /
• pp.22.1-22.3
• /
• 2020

The Medical Subject Headings (MeSH) thesaurus is a controlled vocabulary for indexing biomedical documents that is used for document retrieval and other natural language processing purposes. However, although the oariginal English MeSH is freely available, its Japanese translation has a restricted license. We attempted to create an open alternative, and for this purpose we made a script for assigning MeSH UIDs to Japanese medical terms using Japanese-English glossaries. From the MeSpEn glossary and MEDUTX dictionary, we generated a 12,457-word Japanese-MeSH dictionary.

• Phonetics and Speech Sciences
• /
• v.7 no.1
• /
• pp.133-138
• /
• 2015

The purpose of this study is to provide deeper understanding of how it is possible for people to understand PC communication language they have never seen or heard before without any problem. In order to answer this question, we focused on the vowel variation through which new variants are created (for PC communication), and hypothesized that there is a phonetic constraint which requires the vowel of the variant to be phonetically similar (to the maximum) to the vowel of the original word. Through the corpus analysis of the dictionary of PC communication language, we show that our hypothesis is justified by the fact that most of the variants we collected from the dictionary, that is, 90% of them, conformed to the phonetic constraint we postulated.

• Annual Conference on Human and Language Technology
• /
• 2002.10e
• /
• pp.33-39
• /
• 2002

중국어의 품사 태깅(part-of-speech tagging)을 위해서는 중국어 문장들은 내부 단어간의 명확한 분리가 없기 때문에 단어 분할(word segmentation)과 품사 태깅을 동시에 처리해야 한다. 본 논문은 규칙 기반(rule base)과 사전 기반(dictionary base) 기법을 혼합하여 구현한 단어 분할 시스템을 사용하여 입력 문장을 단어 단위로 분할하고, HMM(hidden Markov model) 기반 통계적 품사 태깅 기법을 사용한다. 특히, 본 논문에서는 주어진 말뭉치(corpus)로부터 자동 학습(automatic training)을 통해 품사 사전을 구축하여 구현된 시스템과 말뭉치간의 독립성을 유지한다. 말뭉치는 중국어 간체와 번체 모두를 대상으로 하고, 각 말뭉치로부터 자동 학습을 통해 얻어진 품사 사전으로 단어 분할과 품사 태깅을 한다. 실험결과들은 간체, 번체 각각의 단어 분할 성능과 품사 태깅 성능을 보여준다.

• Cross-Cultural Studies
• /
• v.19
• /
• pp.233-250
• /
• 2010

This study aims to observe the features of Korean adjectives composed with symbolic base impling human character. Korean adjectives composed with symbolic base shows more delicate nuances than ordinary adjectives. For observing the feature of them we analyzed the 6000 symbolic words in 'Stanadard Korean Dictionary'. As a result,the symbolic base of adjectives is divided into the one that maintain the basic meaning of symbolic words and the other that do not maintain basic meaning of symbolic words. The base that maintain the basic meaning of symbolic words is divided into the one that has meaning of character and the other that do not has meaning of character. The base that do not maintain the basic meaning of symbolic words is divided into the one that can relate with '-hada' and the other that cannot relates with '-hada'. This study remains the problem in future to examine common points of symbolic base.

• Journal of Multimedia Information System
• /
• v.9 no.1
• /
• pp.61-68
• /
• 2022

The importance of online reviews is prevalent as more people access goods or places online and make decisions to visit or purchase. However, such reviews are generally provided by short sentences or mere star ratings; failing to provide a general overview of customer preferences and decision factors. This study explored and broke down restaurant reviews found on Google Maps. After collecting and analyzing 5,427 reviews, we vectorized the importance of words using the TF-IDF. We used a random forest machine learning algorithm to calculate the coefficient of positivity and negativity of words used in reviews. As the result, we were able to build a dictionary of words for positive and negative sentiment using each word's coefficient. We classified words into four major evaluation categories and derived insights into sentiment in each criterion. We believe the dictionary of review words and analyzing the major evaluation categories can help prospective restaurant visitors to read between the lines on restaurant reviews found on the Web.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2154-2168
• /
• 2022

Our work addresses the issues associated with usage of the semantic features by Bag of Words model, which requires construction of the dictionary. Extracting the relevant features and clustering them into code book or dictionary is computationally intensive and requires large storage area. Hence we propose to use a simple distribution of multiple shape based features, which is a mixture of gradients, radius and slope angles requiring very less computational cost and storage requirements but can serve as an equivalent image representative. The experimental work conducted on PASCAL VOC 2007 dataset exhibits marginally closer performance in terms of accuracy with the Bag of Word model using Self Organizing Map for clustering and very significant computational gain.

• The KIPS Transactions:PartB
• /
• v.12B no.7 s.103
• /
• pp.829-840
• /
• 2005

Word Sense Disambiguation(WSD) is one of the most difficult problem in Korean information processing. We propose a WSD model with the capability to filter semantic information using the specific characteristics in dictionary dictions, and nth added information, useful to sense determination, such as statistical, distance and case information. we propose a model, which can resolve the issues resulting from the scarcity of semantic information data based on the word hierarchy system (thesaurus) developed by Ulsan University's UOU Word Intelligent Network, a dictionary-based toxicological database. Among the WSD models elaborated by this study, the one using statistical information, distance and case information along with the thesaurus (hereinafter referred to as 'SDJ-X model') performed the best. In an experiment conducted on the sense-tagged corpus consisting of 1,500,000 eojeols, provided by the Sejong project, the SDJ-X model recorded improvements over the maximum frequency word sense determination (maximum frequency determination, MFC, accuracy baseline) of $18.87\%$ ($21.73\%$ for nouns and inter-eojeot distance weights by $10.49\%$ ($8.84\%$ for nouns, $11.51\%$ for verbs). Finally, the accuracy level of the SDJ-X model was higher than that recorded by the model using only statistical information, distance and case information, without the thesaurus by a margin of $6.12\%$ ($5.29\%$ for nouns, $6.64\%$ for verbs).

• The Journal of the Acoustical Society of Korea
• /
• v.10 no.2
• /
• pp.29-35
• /
• 1991

In this paper, we discuss the method of recognizing allophone unit isolated words using hidden Markov model(HMM). Frist we constructed allophone lexicon by extracting allophones from training data and by training allophone HMMs. And then to recognize isolated words using allophone HMMs, it is necessary to construct word dictionary which contains information of allophone sequence and inter-allophone transition probability. Allophone sequences are represented by allophone HMMs. To see the effects of inter-allophone transition probability and to determine optimal probabilities, we performend some experiments. And we showed that small number of traing data and simple train procedure is needed to train word HMMs of allophone sequences and that not less performance than word unit HMM is obtained.