• International Journal of Advanced Culture Technology
• /
• v.5 no.1
• /
• pp.83-89
• /
• 2017

In this paper, we propose an extended method of one-hot Long Short-Term Memory (LSTM) and evaluate the performance on spam filtering task. Most of traditional methods proposed for spam filtering task use word occurrences to represent spam or non-spam messages and all syntactic and semantic information are ignored. Major issue appears when both spam and non-spam messages share many common words and noise words. Therefore, it becomes challenging to the system to filter correct labels between spam and non-spam. Unlike previous studies on information filtering task, instead of using only word occurrence and word context as in probabilistic models, we apply a neural network-based approach to train the system filter for a better performance. In addition to one-hot representation, using term weight with attention mechanism allows classifier to focus on potential words which most likely appear in spam and non-spam collection. As a result, we obtained some improvement over the performances of the previous methods. We find out using region embedding and pooling features on the top of LSTM along with attention mechanism allows system to explore a better document representation for filtering task in general.

• Phonetics and Speech Sciences
• /
• v.7 no.3
• /
• pp.89-97
• /
• 2015

The aim of this study is to investigate the prosodic aspects of structural ambiguous sentences in Korean produced by Japanese Korean learners and the influence of their first language prosody. Previous studies reported that structural ambiguous sentences in Korean are different especially in prosodic phrasing. So we examined whether Japanese Korean leaners can also distinguish, in production, between two types of structural ambiguous sentences on the basis of prosodic features. For this purpose 4 Korean native speakers and 8 Japanese Korean learners participated in the production test. Analysis materials are 6 sentences where a relative clause modify either NP1 or NP1+NP2. The results show that Korean native speakers produced ambiguous sentences by different prosodic structure depending on their semantic and syntactic structure (left branching or right branching sentence). Japanese speakers also show distinct prosodic structure for two types of ambiguous sentences in most cases, but they have more errors in producing left branching sentences than right branching sentences. In addition to that, interference of Japanese pitch accent in the production of Korean ambiguous sentences was observed.

• Annual Conference on Human and Language Technology
• /
• 1993.10a
• /
• pp.559-570
• /
• 1993

In this article we present a rapid development of a Korean to English translation system, by the help of general English generator, PENMAN. PENMAN is an English sentence generation system, of which input language is a language specially devised for sentence generation, named Sentence Planning Language(SPL). The language SPL has various features that are necessary for generating sentences, covering both syntactic and semantic features. In this development we integrated a Korean language parser based on dependency grammar and the English sentence generator PENMAN, bridging two systems through a converting module, which converts dependency structures produced by Korean parser into SPL for PENMAN.

• Annual Conference on Human and Language Technology
• /
• 2002.10e
• /
• pp.129-136
• /
• 2002

고성능의 질의응답 시스템을 구현하기 위해서는 사용자의 질의 유형의 난이도에 관계없이 의도를 파악할 수 있는 질의유형 분류기가 필요하다. 본 논문에서는 문서 범주화 기법을 이용한 질의 유형 분류기를 제안한다. 본 논문에서 제안하는 질의 유형 분류기의 분류 과정은 다음과 같다. 우선, 사용자 질의에 포함된 어휘, 품사, 의미표지와 같은 다양한 정보를 이용하여 사용자 질의로부터 자질들을 추출한다. 이 과정에서 질의의 구문 특성을 반영하기 위해서 슬라이딩 윈도 기법을 이용한다. 또한, 다량의 자질들 중에서 유용한 것들만을 선택하기 위해서 카이 제곱 통계량을 이용한다. 추출된 자질들은 벡터 공간 모델로 표현되고, 문서 범주화 기법 중 하나인 지지 벡터 기계(support vector machine, SVM)는 이 정보들을 이용하여 질의 유형을 분류한다. 본 논문에서 제안하는 시스템은 질의 유형 분류 문제에지지 벡터 기계를 이용한 자동문서 범주화 기법을 도입하여 86.4%의 높은 분류 정확도를 보였다. 또한 질의 유형 분류기를 통계적 방법으로 구축함으로써 lexico-syntactic 패턴과 같은 규칙을 기술하는 수작업을 배제할 수 있으며, 응용 영역의 변화에 대해서도 안정적인 처리와 빠른 이식성을 보장한다.

• Journal of the Korean Institute of Educational Facilities
• /
• v.18 no.4
• /
• pp.13-24
• /
• 2011

The purpose of this research is to investigate the characteristics of layout of Jinhae's educational facilities from the perspective of space syntactic changes since the era of Japanese Imperialism. The observations that we made in this research are summarized as the following three points. First, most of the educational facilities are located near the integrated space. Axes of roads near educational facilities display similar spatial patterns as those of entire Jinhae. Second, the level of local integration has been rising near the site of elementary schools for the past decades, and the level of local integration near middle and high schools recently began to rise around the new town. Third, the level of integration is strongly related with the levels of local integration, and the locations of educational facilities are also related with the level of local integration. It implies that the locations of educational facilities are determined not by Jinhae's overall street composition but by nearby road composition.

• The KIPS Transactions:PartD
• /
• v.14D no.7
• /
• pp.819-828
• /
• 2007

In this paper, we propose a topic maps matching and merging approach based on the syntactic or semantic characteristics and constraints of the topic maps. Previous schema matching approaches have been developed to enhance effectiveness and generality of matching techniques. However they are inefficient because the approaches should transform input ontologies into graphs and take into account all the nodes and edges of the graphs, which ended up requiring a great amount of processing time. Now, standard languages for developing ontologies are RDF/OWL and Topic Maps. In this paper, we propose an enhanced version of matching and merging technique based on topic partitioning, several matching operations and merging conflict detection.

• The KIPS Transactions:PartD
• /
• v.15D no.1
• /
• pp.113-120
• /
• 2008

Web Services composition has gained a considerable attention because of the widespread use of the Web Services and SOA. Recently, various researches on automatic Web Services composition are on going to realize more dynamic and intelligent SOA environments. However, there is no complete solution for automatic Web Services composition now and previous researches have several problems. Automatic composition based on syntactic information has low correctness through incorrect semantic linking. Moreover, many researches make an process as the result of composition which is hard for actual execution. In this paper, improved automatic Web Services composition based on Web Services choreography is proposed. In this system, the correctness is improved and the result of composition is more concrete process.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.8
• /
• pp.2025-2037
• /
• 1997

The concept-based translation system, which is a part of the Korean spoken language translation system, translates spoken utterances from Korean speech recognizer into one of English, Japanese and Korean in a travel planning task. Our system regulates semantic rather than the syntactic category in order to process the spontaneous speech which tends to be regarded as the one ungrammatical and subject to recognition errors. Utterances are parsed into concept structures, and the generation module produces the sentence of the specified target language. We have developed a token-separator using base-words and an automobile grammar corrector for Korean processing. We have also developed postprocessors for each target language in order to improve the readability of the generation results.

• The KIPS Transactions:PartA
• /
• v.12A no.2 s.92
• /
• pp.109-116
• /
• 2005

In this paper, we introduce the method that a user analyses the similarity of the two programs by using keyword from the syntactic tree, created after the syntax analysis, and its implementation. The main advantage of the method is the performance improvement through using only keyword of syntax tree. In the paper, we propose the similarity evaluation model and how we extract keyword from syntax tree. In addition, we also show the improvement in the performance in analysis and in the system's structure. We expect that our system will be utilized in the similarity evaluation in text and XML documents.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.3
• /
• pp.324-330
• /
• 2010

XML schema is widely used as an effective tool for organizing and validating XML data. Although W3C released XQuery and XQuery Update Facility as the standard methods for searching and updating XML data, there is no consideration about providing facilities for updating XML schema itself until now. So users can only update an XML schema file directly by using editors. However, the direct update has several problems: It cannot prevent user's illegal update; it is hard to apply to the XML schemas stored in databases, needs much time to analyze schema, and is likely to make syntactic errors. In this paper, we propose an XML schema update facility, which enables creation, deletion and modification of XML schema by using commands.