• Korean Journal of Cognitive Science
• /
• v.6 no.2
• /
• pp.5-27
• /
• 1995

Based on the given data if three experiments that measured word-by-word reading times of the Korean relative-clause sentences,parsing strategies and performance structures in comprehending Korean sentences were suggested.First,results of the significantily longer reading time of nouns than verbs suggested that Korean parsing processing would be primarily occurred at nouns.Seond,four parsing strategies were proposed to explain increased reading times,working memory loads,and parallel function effects.Third,performance structures of sentence comprehension were constructed from the interword reading time differences.The proposed strategies and structures seem to account for the patterns of word-by-word reading times of the five types of the Korean relative-clause se various ideas for further experimentation were discussed.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.10
• /
• pp.1193-1201
• /
• 1988

In this paper, we describe the syntactic and semantic parsing methods which use the case frames. The case structures based on obligatory cases of verbs. And, we use a small set of partial-garammar rules based on simple sentence to represent such case structures. Also, we enhance the efficiency by constructing independent procedure for particle classification and ambiguity resolution of major particle considering the importance of Japanese particle process in the generation. And we construct the generation table considering the combination possibility between the verbs and auxiliary verbs for processing the termination phrase. Therefore we can generate more natural translated sentence according to unique decision with information of syntactic analysis and simplify the generating process.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.329-336
• /
• 2006

In this paper, we propose a method of significant term extraction within a document. The technique used is Principal Component Analysis(PCA) which is one of the multivariate analysis methods. PCA can sufficiently use term-term relationships within a document by term-term correlations. We use a correlation matrix instead of a covariance matrix between terms for performing PCA. We also try to find out thresholds of both the number of components to be selected and correlation coefficients between selected components and terms. The experimental results on 283 Korean newspaper articles show that the condition of the first six components with correlation coefficients of |0.4| is the best for extracting sentence based on the significant selected terms.

• The KIPS Transactions:PartB
• /
• v.14B no.2
• /
• pp.107-118
• /
• 2007

This paper proposes a 3D avatar which expresses sign language in a very using lips, facial expression, complexion, pupil motion and body motion as well as hand shape, Hand posture and hand motion to overcome the limitation of conventional sign language avatars from a deaf's viewpoint. To describe motion data of hand and other body components structurally and enhance the performance of databases, we introduce the concept of a hyper sign sentence. We show the superiority of the developed system by a usability test through a questionnaire survey.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.7
• /
• pp.271-276
• /
• 2014

Short message service(SMS) in a mobile communication environment is a very convenient method. However, it caused a serious side effect of generating spam messages for advertisement. Those who send spam messages distort or deform SMS sentences to avoid the messages being filtered by automatic filtering system. In order to increase the performance of spam filtering system, we need to recover the distorted sentences into normal sentences. This paper proposes a method of normalizing the various types of distorted sentence and extracting keywords through automatic word spacing and compound noun decomposition.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2008.10a
• /
• pp.90-93
• /
• 2008

In natural language, it is common that repetitive constituents in an expression are to be left out and it is necessary to figure out the constituents omitted at analyzing the meaning of the sentence. This paper is on recognition of boundaries of parallel noun phrases by figuring out constituents omitted. Recognition of parallel noun phrases can greatly reduce complexity at the phase of sentence parsing. Moreover, in natural language information retrieval, recognition of noun with modifiers can play an important role in making indexes. We propose an unsupervised probabilistic model that identifies parallel cores as well as boundaries of parallel noun phrases conjoined by a conjunctive particle. It is based on the idea of swapping constituents, utilizing symmetry (two or more identical constituents are repeated) and reversibility (the order of constituents is changeable) in parallel structure. Semantic features of the modifiers around parallel noun phrase, are also used the probabilistic swapping model. The model is language-independent and in this paper presented on parallel noun phrases in Korean language. Experiment shows that our probabilistic model outperforms symmetry-based model and supervised machine learning based approaches.

• 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.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.217-220
• /
• 2007

This study outlines a small-sized dialog style ETRI Korean TTS system which applies a HMM based speech synthesis techniques. In order to build the VoiceFont, dialog-style 500 sentences were used in training HMM. And the context information about phonemes, syllables, words, phrases and sentence were extracted fully automatically to build context-dependent HMM. In training the acoustic model, acoustic features such as Mel-cepstrums, logF0 and its delta, delta-delta were used. The size of the VoiceFont which was built through the training is 0.93Mb. The developed HMM-based TTS system were installed on the ARM720T processor which operates 60MHz clocks/second. To reduce computation time, the MLSA inverse filtering module is implemented with Assembly language. The speed of the fully implemented system is the 1.73 times faster than real time.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.3
• /
• pp.1-5
• /
• 2002

In this paper, we present an improved grammatical structure of the finite state network(FSN) for constructing useful recognizer of practical Korean price sentences. The grammar constraints of Korean price sentences in the existing method are necessary to modify grammar constraint and grammatical structure for the recognition of practical Korean price sentences. The grammar constraints are improved in the third and the fourth grammar constraint of Korean price sentences for the practical point. In this paper, we improve the grammar constraints and make up for the weak point in the grammatical structure of the FSN[1]. Three kinds of experiments were performed to evaluate the improved grammatical structures; FSN0, FSN-1, FSN-2. As the recognition results for price sentences, the word recognition rates were 81.37%, 83.92%, and 85.49%, for FSN0, FSN-1, and FSN-2. Also, the sentence recognition rates were 35％, 45%, and 52％, respectively.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.1
• /
• pp.184-194
• /
• 1997

In the recent years number of commercial off-line character recognition systems have been appeared in the Korean market. This paper describes a "self -organizing" data structure for representing a large dictionary which can be searched in real time and uses a practical amount of memory, and presents a study on the character correction for off-line printed sentence marks, Japanese, English, and Chinese character recognition. Self-organizing algorithm can be recommenced as particularly appropriate when we have reasons to suspect that the accessing probabilities for individual words will change with time and theme. The wrongly recognized characters generated by OCR systems are collected and analyzed Error types of English characters are reclassified and 0.5% errors are corrected using an English character confusion table with a self-organizing dictionary containing 25,145 English words. And also error types of Chinese characters are classified and 6.1% errors are corrected using a Chinese character confusion table with a self-organizing dictionary carrying 34,593 Chinese words.ese words.