• Journal of KIISE:Software and Applications
• /
• v.37 no.12
• /
• pp.946-950
• /
• 2010

Many sentiment categorization systems based on machine learning methods use morphological analyzers in order to extract linguistic features from sentences. However, the morphological analyzers do not generally perform well in a customer review domain because online customer reviews include many spacing errors and spelling errors. These low performances of the underlying systems lead to performance decreases of the sentiment categorization systems. To resolve this problem, we propose a feature extraction method based on simple longest matching of Eojeol (a Korean spacing unit) and phoneme patterns. The two kinds of patterns are automatically constructed from a large amount of POS (part-of-speech) tagged corpus. Eojeol patterns consist of Eojeols including content words such as nouns and verbs. Phoneme patterns consist of leading consonant and vowel pairs of predicate words such as verbs and adjectives because spelling errors seldom occur in leading consonants and vowels. To evaluate the proposed method, we implemented a sentiment categorization system using a SVM (Support Vector Machine) as a machine learner. In the experiment with Korean customer reviews, the sentiment categorization system using the proposed method outperformed that using a morphological analyzer as a feature extractor.

• Korean Journal of Cognitive Science
• /
• v.12 no.3
• /
• pp.1-18
• /
• 2001

The goal of this paper is the pedagogical application of a Korean Spell/Grammar Checker to the web-based language learning system for Korean writing. To maximize the efficient instruction of our learning system \\`Urimal Baeumteo\\` we have to improve our Korean Spell/Grammar Checker. Today the NLP system\\`s performance defends on its semantic processing capability. In our Korean Spell/Grammar Checker. the tasks accomplished in the semantic level are: the detection and correction of misused derived and compound nouns in a Korean spell-checking device and the detection and correction of syntactic and semantic errors in a Korean grammars-checking device. We describe a common approach to the partial parsing using collocation rules based on the dependency grammar. To provide more detailed semantic rules. we classified nouns according to their concepts. and subcategorized verbs referring to their syntactic and semantic features. Improving a Korean Spell/Gl-Grammar Checker makes our learning system active and intelligent in a web-based environment. We acknowledge the flaws in our system: the classification of nouns based on their meanings and concepts is a time consuming task. the analytic unit of this study is principally limited to the phrases in a sentence therefore the accurate parsing of embedded sentences remains a difficult problem to solve. Concerning the web-based language learning system. it is critically important to consider its interface design and structure of its contents.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.12
• /
• pp.2153-2158
• /
• 2008

XML is one of standard web languages. XML has a syntax architecture consisted of tags, which are used to descript contents and structures of a XML document. In XML documents, missing of markup tag is one of common factors generating incomplete inputs. Usually, editors will recognize incomplete inputs as syntax errors. And so, when editors find them, they will highlight lines in which syntax errors happened, and execute appropriate error handling routines. But, there are no more parsing actions. In this paper, we propose a method to recognize incomplete input strings and keep parsing phases going. To recognize pars missed grammatically in incomplete inputs and create them newly, we use an expanding parsing table. It includes additional parsing actions for newly generated input symbols. Through the information, incomplete inputs will be completed and parsing steps will be finished successively. Therefore, users can be assured that they make always correct XML documents, even if inputs are incomplete, and can not be nervous about input faults.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.11
• /
• pp.441-448
• /
• 2019

Previous researches on automatic spacing of Korean sentences has been researched to correct spacing errors by using n-gram based statistical techniques or morpheme analyzer to insert blanks in the word boundary. In this paper, we propose an end-to-end automatic word spacing by using deep neural network. Automatic word spacing problem could be defined as a tag classification problem in unit of syllable other than word. For contextual representation between syllables, Bi-LSTM encodes the dependency relationship between syllables into a fixed-length vector of continuous vector space using forward and backward LSTM cell. In order to conduct automatic word spacing of Korean sentences, after a fixed-length contextual vector by Bi-LSTM is classified into auto-spacing tag(B or I), the blank is inserted in the front of B tag. For tag classification method, we compose three types of classification neural networks. One is feedforward neural network, another is neural network language model and the other is linear-chain CRF. To compare our models, we measure the performance of automatic word spacing depending on the three of classification networks. linear-chain CRF of them used as classification neural network shows better performance than other models. We used KCC150 corpus as a training and testing data.

• Phonetics and Speech Sciences
• /
• v.12 no.4
• /
• pp.27-36
• /
• 2020

The aim of this study is to investigate the perceptive aspects of the polysemic sentence final ending "-(eu)lgeol" produced by Chinese Korean learners. "-(Eu)lgeol" has two different meanings, that is, a guess and a regret, and these different meanings are expressed by the different prosodic features of the last syllable of "-(eu)lgeol". To examine how Korean native speakers perceive "-(eu)lgeol" sentences produced by Chinese Korean learners and the most saliant prosodic variable for the semantic discrimination of "-(eu)lgeol" at the perceptive level, we performed a perceptual experiment. The analysed material constituted four Korean sentences containing "-(eu)lgeol" in which two sentences expressed guesses and the other two expressed regret. Twenty-five Korean native speakers participated in the perceptual experiment. Participants were asked to mark whether "-(eu)lgeol" sentences they listened to were (1) definitely regrets, (2) probably regrets, (3) ambiguous, (4) probably guesses, or (5) definitely guesses based on the prosodic features of the last syllable of "-(eu)lgeol". The analysed prosodic variables were sentence boundary tones, slopes of boundary tones, pitch difference between sentence-final and penultimate syllables, and pitch levels of boundary tones. The results show that all the analysed prosodic variables are significantly correlated with the semantic discrimination of "-(eu)lgeol" and among these prosodic variables, the most salient role in the semantic discrimination of "-(eu)lgeol" is pitch difference between sentence-final syllable and penultimate syllable.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• pp.249-252
• /
• 1994

Keyword spotting 이란 음성인식의 한 분야로서 컴퓨터가 사람의 음성을 입력받아 이 음성에 미리 정해진 특정단어 또는복수개의 단어들 중 어느 것이 포함되어 있는지의 여부를 찾아내고 이 단어를 식별해 내는 작업을 의미한다. 이러한 keyword spotting 시스템의 인식 오류들을 감소시키는 방법의 하나로 keyword spotting 시스템에 후처리 과정을 둠으로써 잘못 검출된 keyword 들을 제거시키는 방법이 사용될 수 있다. 본 논문에서는 keyword로 검출된 영역에 대한 keyword 모델의 likeihood와 그 여역에 대한 filler 모델의 likelihood의 ratio 와 second best keyword 의 likelihood 그리고, 끝점존재 영역의 구간 길이등 여러 가지 정보를 이용한 후처리과정을 검토하고 인식실험을 통해 이들의 성능을 비교하였다. 6개의 부서명을 keyword로 하는 불특정 화자 keyword spotting 실험을 수행한 결과 baseline 시스템의 경우 고립단어 및 문장 형태의 음성에 대해 95.0%의 keyword 인식률을 얻었으며, 본 논문에서 검토된 네 가지 후처리 방법에 의해 keyword rejection ratio를 0%에서 5%까지 변화시켜 나갈 경우 최저 95.3%에서 최고 97.1%까지 keyword 인식률이 향상된 결과를 얻었다. 특히 성능과 계산량을 종합적으로 고려할 때 끝점 존재 영역의 구간 길이 정보를 이용한 방법이 가장 우수하였다.

• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.116-121
• /
• 1997

한국어 문장에서 술어의 역할이 매우 중요하기 때문에 술어의 하위범주화 정보는 한국어 분석 및 생성에서 필수적이다. 그러나 기존의 한국어 술어의 하위범주화 사전은 전문가의 사전지식이나 직관에 의존하여 만들어졌기 때문에 주관적이고 오류의 가능성이 높으며 많은 수작업이 필요했다. 또 영역에 독립적인 하위범주화 정보를 구축하는 작업은 매우 어렵기 때문에 응용영역에 맞는 하위범주화 정보를 쉽게 구축하는 방법이 요구되었다. 본 논문에서는 구문구조부착 말뭉치를 이용하여 전문가의 제한된 개입만으로 통계정보와 명사의 의미정보를 포함하는 술어의 하위범주화 정보 구축 방법을 제안한다.

• Annual Conference on Human and Language Technology
• /
• 2003.10d
• /
• pp.227-231
• /
• 2003

한극 문서의 자동 띄어쓰기는 웹 문서와 검색 질의어, 법률안 제목, 문자 메시지 등에서 띄어쓰지 않은 문장에 대해 자동으로 공백을 삽입해 주는 기능이다. 기존의 자동 띄어쓰기 기법은 각 문자 경계마다 공백 삽입 일치도를 비교하는 방식으로 평가되었으나, 실제 응용 시스템에서는 어절 인식 정확률이 높고, 공백의 과생성 오류가 적으며, 바이그램 데이터 크기가 작아야 한다. 본 논문에서는 이러한 요구 조건에 따라 새로운 평가 기준을 제시하고, 이에 따라 기존 방법보다 바이그램 데이터 크기가 매우 작고, 정확률이 높은 자동 띄어씌기 방법을 제안하였다.

• The Mathematical Education
• /
• v.38 no.1
• /
• pp.77-85
• /
• 1999

In this paper, we analyze strategies and error patterns in solving word problems of linear equation for middle school students. From a test conducted to the sampled 106 second grade middle school students, we obtain the following results: (1)The most difficult types of word problem are velosity and density related problems. The second one is length related problems and the easist one is number related problems. (2)Regardless of the types of word problem, the most familiar strategy is the constructing algebraic equations. However, the most successful strategy is the trial and error. (3)Most likely error patterns are the use of inadequate formulas and wrong trial and errors. Based on these results, a teaching program with various schema is developed and shown to be effective for mid level students in classroom.

• Journal of Internet Computing and Services
• /
• v.2 no.4
• /
• pp.55-67
• /
• 2001

Commercial machine translation systems have been announcing recently, However, there are problems that the systems have shown mistranslations, yet. Among these mistranslations, this paper is interested in the mistakes of tense processing. The paper compares Korean tenses with 12 English ones: present. past, future, present perfect. past perfect, future perfect. present progressive, past progressive, future progressive, present perfect progressive, past perfect progressive. future perfect progressive. Next, we perform the meaning analysis of Korean tenses. Then we describe the structure of the tenses based on Conceptual Graph(CG). In the experiment. the paper implements the program that translates sentences included in the tenses into CG.