• The Transactions of the Korea Information Processing Society
• /
• v.7 no.9
• /
• pp.2876-2884
• /
• 2000

Clausal segmentation is the method that parses Korean sentences by segmenting one long sentence into several phrases according to the predicates. So far most of researches could be useful for literary sentences, but long sentences increase complexities of the syntax analysis. Thus this paper proposed Two-Level Clausal Segmentation using sense information which was designed and implemented to solve this problem. Analysis of clausal segmentation and understanding of word senses can reduce syntactic and semantic ambiguity. Clausal segmentation using Sense Information is necessary because there are structural ambiguity of sentences and a frequent abbreviation of auxiliary word in common sentences. Two-Level Clausal Segmentation System(TLCSS) consists of Complement Selection Process(CSP) and Noncomplement Expansion Process(NEP). CSP matches sentence elements to subcategorization dictionary and noun thesaurus. As a result of this step, we can find the complement and subcategorization pattern. Secondly, NEP is the method that uses syntactic property and the others methods for noncomplement increase of growth. As a result of this step, we acquire segmented sentences. We present a technique to estimate the precision of Two-Level Clausal Segmentation System, and shows a result of Clausal Segmentation with 25,000 manually sense tagged corpus constructed by ETRl-KONAN group. An Two-Level Clausal Segmentation System shows clausal segmentation precision of 91.8%.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.1
• /
• pp.247-252
• /
• 1999

In order to realize a speech coding at low bit rates, a pitch information is useful parameter. In case of extracting an average pitch information form continuous speech, the several pitch errors appear in a frame which consonant and vowel are coexistent; in the boundary between adjoining frames and beginning or ending of a sentence. In this paper, I propose an Individual Pitch (IP) extraction method using residual signals of the FIR-STREAK digital filter in order to restrict the pitch extraction errors. This method is based on not averaging pitch intervals in order to accomodate the changes in each pitch interval. As a result, in case of Ip extraction method suing FIR-STREAK digital filter, I can't find the pitch errors in a frame which consonant and vowel are consistent; in the boundary between adjoining frames and beginning or ending of a sentence. This method has the capability of being applied to many fields, such as speech coding, speech analysis, speech synthesis and speech recognition.

• Korean Journal of Cognitive Science
• /
• v.16 no.2
• /
• pp.69-92
• /
• 2005

A brief survey of linguistic studies on the nature of contrastive information in discourse was Presented first, and an attempt was also made to incorporate the Linguistic theories and concepts about contrast in discourse into a psychological framework. A tentative model of processing of contrastive information in discourse was Proposed, and eight experimental studies on the effects of contrastive information on comprehension and memory of short and ions discourses were reviewed. Experimental results showed that contrastive sentences took more time to process at encoding, and yet were recognized faster and cued-recalled in greater amount than noncontrastive sentences. It was also found that levels of contrast in the discourse structure have some effects on encoding time. It was further found that the sentence immediately following the contrastive sentence was processed slowly regardless of whether it does or does not resolve the contrast. The implications of the results of empirical studies were discussed in relation to developing a research framework that integrate coherence studies and contrast studies urns the two disciplines of linguistics and cognitive psychology.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.10
• /
• pp.1000-1004
• /
• 2010

A large number of current language processing systems use a part-of-speech tagger for preprocessing. Most language processing systems required a tagger with the highest possible accuracy. Specially, the use of domain-specific advantages has become a hot issue in machine translation community to improve the translation quality. This paper addresses a method for customizing an HMM or LHMM based English tagger from general domain to specific domain. The proposed method is to semi-automatically customize the output and transition probabilities of HMM or LHMM using domain-specific raw corpus. Through the experiments customizing to Patent domain, our LHMM tagger adapted by the proposed method shows the word tagging accuracy of 98.87% and the sentence tagging accuracy of 78.5%. Also, compared with the general tagger, our tagger improved the word tagging accuracy of 2.24% (ERR: 66.4%) and the sentence tagging accuracy of 41.0% (ERR: 65.6%).

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.3
• /
• pp.129-136
• /
• 2019

There are a variety of entities in natural language such as people, organizations, places, and products. These entities can have many various meanings. The ambiguity of entity is a very challenging task in the field of natural language processing. Entity Linking(EL) is the task of linking the entity in the text to the appropriate entity in the knowledge base. Pairwise based approach, which is a representative method for solving the EL, is a method of solving the EL by using the association between two entities in a sentence. This method considers only the interdependence between entities appearing in the same sentence, and thus has a limitation of global interdependence. In this paper, we developed an Entity2vec model that uses Word2vec based on knowledge base of RDF type in order to solve the EL. And we applied the algorithms using the generated model and ranked each entity. In this paper, to overcome the limitations of a pairwise approach, we devised a pairwise approach based on comprehensive interdependency and compared it.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.24-29
• /
• 2022

Semantic role labeling task used in various natural language processing fields, such as information extraction and question answering systems, is the task of identifying the arugments for a given sentence and predicate. Predicate used as semantic role labeling input are extracted using lexical analysis results such as POS-tagging, but the problem is that predicate can't extract all linguistic patterns because predicate in korean language has various patterns, depending on the meaning of sentence. In this paper, we propose a korean predicate recognition method using neural network model with pre-trained embedding models and lexical features. The experiments compare the performance on the hyper parameters of models and with or without the use of embedding models and lexical features. As a result, we confirm that the performance of the proposed neural network model was 92.63%.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.3
• /
• pp.160-165
• /
• 2023

In this study, we propose an SNS sentence writing assistance system that utilizes YOLO and GPT to assist users in writing texts with images, such as SNS. We utilize the YOLO model to extract objects from images inserted during writing, and also extract meta-information such as GPS information and creation time information, and use them as prompt values for GPT. To use the YOLO model, we trained it on form image data, and the mAP score of the model is about 0.25 on average. GPT was trained on 1,000 blog text data with the topic of 'restaurant reviews', and the model trained in this study was used to generate sentences with two types of keywords extracted from the images. A survey was conducted to evaluate the practicality of the generated sentences, and a closed-ended survey was conducted to clearly analyze the survey results. There were three evaluation items for the questionnaire by providing the inserted image and keyword sentences. The results showed that the keywords in the images generated meaningful sentences. Through this study, we found that the accuracy of image-based sentence generation depends on the relationship between image keywords and GPT learning contents.

• MALSORI
• /
• no.62
• /
• pp.33-49
• /
• 2007

The purpose of this study is 1) to investigate the phoneme inventories and phonological processes of cochlear implant(CI) children and 2) to describe their utterances using narrow phonetic transcription method. All ten subjects had more than 2 year-experience with CI and showed more than 85 % open-set sentence perception abilities. Average consonant accuracy was 81.36 % and it was improved up to 87.41% when distortion errors were not counted. They showed similar phonological processing patterns to HA or normal hearing children in some way as well as different phonological processing patterns from HA or normal hearing children. The prominent distortion error pattern was weakening of consonants. Every subject had his/her idiosyncratic error pattern that demanded his/her own individualized therapy program.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.621-624
• /
• 2006

본 논문은 기존의 수화 발생 시스템이 갖는 처리 성능의 한계와 신체요소의 움직임에 대한 문제점을 지적하고, 이를 개선하기 위해 하이퍼 수화문장을 제안한다. 하이퍼 수화문장은 기존 수화문장의 구조를 확장하여 수화단어와 신체효소의 동작기호로 구성된 수화문장이다. 제안한 하이퍼 수화문장 생성 방법에 따라 하이퍼 수화어절을 연결하여 수화동작을 합성하고 수화문장에 대한 아바타의 움직임을 실제 수화자와 유사하게 생성하는 시스템을 보인다.

• Korean Journal of Cognitive Science
• /
• v.2 no.1
• /
• pp.51-72
• /
• 1990

This study investigated the effects of macrostructure on discourse processing. In this study, three different story were employed to form macrostructures on different times, and reading time, sentence verification time and free recall rate were measured as dependent vari- ables. The results showed that forming the macrostructure influenced the reading and verification times and the recall rate. The results were interpreted to indicate that the macrostructure is important to comprehend and recall the stories, and that the story grammars, hierarchies of story schema and causal relation of sentences affect the comprehension and recall through their interaction in macrostructure.