• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.5
• /
• pp.127-137
• /
• 1996

In this paper, an algorithm for on-line rightward japanese parsing is proposed. The ambiguity in on-line parsing is accumulated until the input is completely finished, since there is not a space between words in the japanese sentence. Thus the algorithm for morphological analysis, based on modified chart, is used in solving it. And the number of searching a word in dirctionary for morphological analysis is also a puzzling problem. The japanese sentence, consist of N characters, has logically its maximum number of N(N+1)/2 searches in the ordinary on-line analysis, which is nearly twice as many as normal off-line. In this paper, the matter is settled through the modification of dictionary format. In experiment, we can accomplish the rate of analysis which is nearly equal to that of off-line parsing. And it becomes clear that the longer a sentence is, the better an analysis efficiency is.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.12
• /
• pp.83-92
• /
• 2011

Typographical errors by the author's mistyping occur frequently in a document being prepared with word processors contrary to usual publications. Preparing this online document, the most common orthographical errors are spelling errors resulting from incorrectly typing intent keys to near keys on keyboard. Typical spelling checkers detect and correct these errors by using morphological analyzer. In other words, the morphological analysis module of a speller tries to check well-formedness of input words, and then all words rejected by the analyzer are regarded as misspelled words. However, if morphological analyzer accepts even mistyped words, it treats them as correctly spelled words. In this paper, I propose a simple method capable of detecting and correcting errors that the previous methods can not detect. Proposed method is based on the characteristics that typographical errors are generally not repeated and so tend to have very low frequency. If words generated by operations of deletion, exchange, and transposition for each phoneme of a low frequency word are in the list of high frequency words, some of them are considered as correctly spelled words. Some heuristic rules are also presented to reduce the number of candidates. Proposed method is able to detect not syntactic errors but some semantic errors, and useful to scoring candidates.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.179-186
• /
• 2021

We have been developed the smart tourism app and the Instagram and YouTube contents to provide personalized tourism information and travel product information to individual tourists. In this paper, we develop a rule-based smart tourism chatbot with the khaiii (Kakao Hangul Analyzer III) morphological analyzer and Neo4J graph database. In the proposed chatbot system, we use a morpheme analyzer, a proper noun dictionary including tourist destination names, and a general noun dictionary including containing frequently used words in tourist information search to understand the intention of the user's question. The tourism knowledge base built using the Neo4J graph database provides adequate answers to tourists' questions. In this paper, the nodes of Neo4J are Area based on tourist destination address, Contents with property of tourist information, and Service including service attribute data frequently used for search. A Neo4J query is created based on the result of analyzing the intention of a tourist's question with the property of nodes and relationships in Neo4J database. An answer to the question is made by searching in the tourism knowledge base. In this paper, we create the tourism knowledge base using more than 1300 Jeju tourism information used in the smart tourism app. We plan to develop a multilingual smart tour chatbot using the named entity recognition (NER), intention classification using conditional random field(CRF), and transfer learning using the pretrained language models.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.3
• /
• pp.47-56
• /
• 1999

Various phonological alteration occurs when we pronounce continuously in korean. This phonological alteration is one of the major reasons which make the speech recognition of korean difficult. This paper presents a rule-based system which converts a speech recognition character string to a text-based character string. The recovery results are morphologically analyzed and only a correct text string is generated. Recovery is executed according to four kinds of rules, i.e., a syllable boundary final-consonant initial-consonant recovery rule, a vowel-process recovery rule, a last syllable final-consonant recovery rule and a monosyllable process rule. We use a x-clustering information for an efficient recovery and use a postfix-syllable frequency information for restricting recovery candidates to enter morphological analyzer. Because this system is a rule-based system, it doesn't necessitate a large pronouncing dictionary or a phoneme dictionary and the advantage of this system is that we can use the being text based morphological analyzer.

• Journal of Digital Convergence
• /
• v.14 no.11
• /
• pp.267-273
• /
• 2016

Creation and Sharing of information which is structured data as well as various unstructured data. makes progress actively through the spread of mobile. Recently, Big Data extracts the semantic information from SNS and data mining is one of the big data technique. Especially, the general emotion analysis that expresses the collective intelligence of the masses is utilized using large and a variety of materials. In this paper, we propose the emotion prediction system architecture which extracts the significant keywords from social network paragraphs using n-gram and Korean morphological analyzer, and predicts the emotion using SVM and these extracted emotion features. The proposed system showed 82.25% more improved recall rate in average than previous systems and it will help extract the semantic keyword using morphological analysis.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.559-560
• /
• 2017

Recently, as the problem of personal information leakage has emerged, studies on data collection and web document classification have been made. The existing system judges only the existence of personal information, and there is a problem in that unnecessary data is not filtered because classification of documents published by the same name or user is not performed. In this paper, we propose a system that can identify the types of data or homonyms using the crawler and morphological analyzer for solve the problem. The user collects personal information on the web through the crawler. The collected data can be classified through the morpheme analyzer, and then the leaked data can be confirmed. Also, if the system is reused, more accurate results can be obtained. It is expected that users will be provided with customized data.

• Journal of KIISE
• /
• v.43 no.4
• /
• pp.430-436
• /
• 2016

Processing of unknown words such as proper nouns and newly coined words is important for a morphological analyzer to process documents in various domains. In this study, a segmentation and tagging method for unknown Korean words is proposed for the 3-step probabilistic morphological analysis. For guessing unknown word, it uses rich suffixes that are attached to open class words, such as general nouns and proper nouns. We propose a method to learn the suffix patterns from a morpheme tagged corpus, and calculate their probabilities for unknown open word segmentation and tagging in the probabilistic morphological analysis model. Results of the experiment showed that the performance of unknown word processing is greatly improved in the documents containing many unregistered words.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2005.06a
• /
• pp.534-539
• /
• 2005

Particle image analyzer for measuring droplet size has been developed. Image processing technique was used with relaxation method. The morphological method based on partial curvature information of pre-processed images was adopted for recognition and separation of overlapped particles. The measurement results show that the present method may be reliable for the analysis of the size and distribution of droplets produced by water mist spay flow.

• Language and Information
• /
• v.2 no.2
• /
• pp.121-154
• /
• 1998

The morphological analyzer is expected to tell attested word forms from imaginable yet unattested ones. An account of the inflectional morphology of English verbs is given in the framework of Word-and-Paradigm morphology, developed mainly by Matthews (1972, 1974, 1991) and further by Aronoff (1994) and Zwicky (1985, 1988), which is free of overrecognition. Thirteen inflectional classes are identified according to the patterns each of them exhibits in filling the slots in the paradigm. Peculiarity in orthography is also considered in assigning each verb lexeme to a class. Modules of a C program which gives associated morphosyntactic properties to all and only attested verb forms are written so that details of this framework can be evaluated explicitly. This program is shown to be superior to existing programs in economy and in the generality it achieves.

• Annual Conference on Human and Language Technology
• /
• 1999.10d
• /
• pp.92-98
• /
• 1999

본 논문에서는 연세대학교 컴퓨터과학과에서 연구되어 온 형태소 분석 시스템에 대해 설명한다. 연세대학교 자연 언어 처리 시스템의 기본적인 바탕은 무엇보다도 대량의 말뭉치를 기반으로 하고 있다는 점이다. 예컨대, 형태소 분석 사전은 말뭉치 처리에 의해 재구성 되었으며, 3000만 어절로부터 추출되어 수작업에 의해 다듬어진 어휘 데이터베이스는 형태소 분석 결과의 상당 부분을 제한하여 일차적인 중의성 해결의 역할을 담당한다. 또한 복합어 분석 역시 말뭉치에서 얻어진 사전을 바탕으로 이루어진다. 품사 태깅은 bigram hmm에 기반하고 있으며 어휘 규칙 등에 의한 후처리가 보강되어 있다. 이렇게 구성된 형태소 분석기 및 품사 태거는 구문 분석기와 함께 연결되어 이용되고 있다.