• ETRI Journal
• /
• 제28권6호
• /
• pp.807-810
• /
• 2006

This letter presents a prediction model for sentence-final intonations for Korean conversational-style text-to-speech systems in which we introduce the linguistic feature of 'modality' as a new parameter. Based on their function and meaning, we classify tonal forms in speech data into tone types meaningful for speech synthesis and use the result of this classification to build our prediction model using a tree structured classification algorithm. In order to show that modality is more effective for the prediction model than features such as sentence type or speech act, an experiment is performed on a test set of 970 utterances with a training set of 3,883 utterances. The results show that modality makes a higher contribution to the determination of sentence-final intonation than sentence type or speech act, and that prediction accuracy improves up to 25% when the feature of modality is introduced.

• Journal of Advanced Marine Engineering and Technology
• /
• 제28권2호
• /
• pp.228-236
• /
• 2004

In this paper. we present a neuro-fuzzy controller which unifies both fuzzy logic and multi-layered feed forward neural networks. Fuzzy logic provides a means for converting linguistic control knowledge into control actions. On the other hand. feed forward neural networks provide salient features. such as learning and parallelism. In the proposed neuro-fuzzy controller. the parameters of membership functions in the antecedent part of fuzzy inference rules are identified by using the error back propagation algorithm as a learning rule. while the coefficients of the linear combination of input variables in the consequent part are determined by using the least square estimation method. Finally. the effectiveness of the proposed controller is verified through computer simulation for an inverted pole system.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.385-393
• /
• 2007

Corpora annotated with lots of linguistic information are required to develop robust and statistical natural language processing systems. Building such corpora, however, is an expensive, labor-intensive, and time-consuming work. To help the work, we design and implement an annotation tool for establishing a Korean dependency tree-tagged corpus. Compared with other annotation tools, our tool is characterized by the following features: independence of applications, localization of errors, powerful error checking, instant annotated information sharing, user-friendly. Using our tool, we have annotated 100,904 Korean sentences with dependency structures. The number of annotators is 33, the average annotation time is about 4 minutes per sentence, and the total period of the annotation is 5 months. We are confident that we can have accurate and consistent annotations as well as reduced labor and time.

• International Journal of Automotive Technology
• /
• 제3권3호
• /
• pp.89-94
• /
• 2002

This paper presents an architecture for distributed control systems and its underlying methodological framework. Ideas and concepts of distributed systems, artificial intelligence, and soft computing are merged into a unique architecture to provide cooperation, flexibility, and adaptability required by knowledge processing in intelligent control systems. The distinguished features of the architecture include a local problem solving capability to handle the specific requirements of each part of the system, an evolutionary case-based mechanism to improve performance and optimize controls, the use of linguistic variables as means for information aggregation, and fuzzy set theory to provide local control. A distributed traffic control system application is discussed to provide the details of the architecture, and to emphasize its usefulness. The performance of the distributed control system is compared with conventional control approaches under a variety of traffic situations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권8호
• /
• pp.3169-3181
• /
• 2015

Nowadays, online word-of-mouth has become a powerful influencer to marketing and sales in business. Opinion mining and sentiment analysis is frequently adopted at market research and business analytics field for analyzing word-of-mouth content. However, there still remain several challengeable areas for 1) sentiment analysis aiming for Korean word-of-mouth content in film market, 2) availability of machine learning models only using linguistic features, 3) effect of the size of the feature set. This study took a sample of 10,000 movie reviews which had posted extremely negative/positive rating in a movie portal site, and conducted sentiment analysis with four machine learning algorithms: naïve Bayesian, decision tree, neural network, and support vector machines. We found neural network and support vector machine produced better accuracy than naïve Bayesian and decision tree on every size of the feature set. Besides, the performance of them was boosting with increasing of the feature set size.

• 대한음성학회지:말소리
• /
• 제63호
• /
• pp.23-46
• /
• 2007

The purpose of this paper is to compare linguistic features of meter in Amoretti and Sonnets from the Portuguese. Amoretti was composed in the 16th century and Sonnets from the Portuguese in the 19th century. Two poems are very strict in satisfying $^*<_I$(LS that makes a lexical stress matched on a strong position. But they allow a peaked monosyllabic word to be matched on a weak position only if it does not violate $^*(\dot{\sigma}\;{\sigma})$. Syntactic inversions which are found in two poems occur to satisfy metrical constraints and rhyme. Particularly, syntactic inversions for rhyme are mainly found in Amoretti, but are rare in Sonnets from the Portuguese which includes many enjambment lines. Furthermore, this paper shows that syntactic inversions can be explained by the interaction of constraints, such as metrical constraints, SCI, and Binary Foot.

• Journal of Advanced Marine Engineering and Technology
• /
• 제20권4호
• /
• pp.11-19
• /
• 1996

Recently, fuzzy and neural network techniques have been successfully applied to control of complex and ill-defined system in a wide variety of areas, such as robot, water purification, automatic train operation system and automatic container crane operation system, etc. In this paper, we present a neuro-fuzzy controller which unifies both fuzzy logic and multi-layered feedforward neural networks. Fuzzy logic provides a means for converting linguistic control knowledge into control actions. On the other hand, feedforward neural networks provide salient features, such as learning and parallelism. In the proposed neuro-fuzzy controller, the parameters of membership functions in the antecedent part of fuzzy inference rules are identified by using the error backpropagation algorithm as a learning rule, while the coefficients of the linear combination of input variables in the consequent part are determined by using the least square estimation method. Finally, the effectiveness of the proposed controller is verified through computer simulation of an inverted pendulum system.

• Journal of Information Technology Applications and Management
• /
• 제10권4호
• /
• pp.29-50
• /
• 2003

This research provide the basic information to enhance the user-orientedness of usability design guidelines for software products and an effective empirical guidance to classify design attributes of internet shopping mall sites. The results of analysis show that design attributes can be classified into the procedural attribute group, the shopping tool attribute group, the visual attribute group, linguistic attribute group, and others. The results show that shopping tool attribute group can be divided further into the search tool attribute group and purchase tool attribute group and that the visual attribute group can be divided further into the screen condition attribute group and the character legibility attribute group. The research reveals that when designers design software interfaces and features they should take the compound effect of a group of design attributes into consideration to enhance the usability of the system.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2016년도 제28회 한글 및 한국어 정보처리 학술대회
• /
• pp.85-89
• /
• 2016

프레임넷 (FrameNet) 프로젝트는 버클리에서 1997년에 처음 제안했으며, 최근에는 다양한 언어적 특징을 반영하여 여러 국가에서 사용되고 있다. 하지만 문장의 프레임을 분석하는 것은 자연언어처리 전문가들이 많은 시간을 들여야 한다. 이 때문에, 한국어 프레임넷을 처음 만들 때는 충분한 훈련을 받은 번역가들이 영어 프레임넷의 문장들과 그 주석 정보들을 직접 번역하는 방법을 사용했다. 결과적으로 상대적으로 적은 비용이 들지만, 여전히 한 문장에 여러 번 등장하는 프레임 정보를 모두 번역하고 에러를 분석해야 했기에 많은 노력이 들어갔다. 본 연구에서는 일본어와 한국어의 언어적 유사성을 사용하여 비교적 적은 비용으로 한국어 프레임넷을 확장하는 방법을 제시한다. 또한 프레임넷에 친숙하지 않은 사용자가 더욱 쉽게 프레임 정보를 활용할 수 있도록 PubAnnotation 기술을 도입하고 "조사"라는 특성을 고려한 Valence pattern 분류를 통해 한국어 공개 프레임넷 사이트를 개선하였다.

• IEIE Transactions on Smart Processing and Computing
• /
• 제2권3호
• /
• pp.103-116
• /
• 2013

This paper reviews various bitstream syntax and parser description (BSPD) languages used in MPEG multimedia standards. Traditionally, the bitstream syntax and semantics have been described in human-readable form. Several languages have been developed to describe the bitstream syntax using a computer-readable language and allow the automatic generation of bitstream parsing function from the description. The languages were designed for different objectives and applications but have a range of commonalities in functionality. The aim of this paper is to provide a historical overview of BSPD languages. The background and target application of the BSPD languages are reviewed. In addition, the technical features of each languages, including the linguistic basis (e.g., XML-based) and parser generation method, are discussed and evaluated. In addition, previous studies based on each language are introduced and categorized according to their objectives. Finally, the relevant technical issues that suggest the direction of the future researches are reported.