• Journal of the Korean Society for Library and Information Science
• /
• v.45 no.2
• /
• pp.251-275
• /
• 2011

In this paper, we propose a novel kernel called a semantic parse tree kernel that extends the parse tree kernel previously studied to extract protein-protein interactions(PPIs) and shown prominent results. Among the drawbacks of the existing parse tree kernel is that it could degenerate the overall performance of PPI extraction because the kernel function may produce lower kernel values of two sentences than the actual analogy between them due to the simple comparison mechanisms handling only the superficial aspects of the constituting words. The new kernel can compute the lexical semantic similarity as well as the syntactic analogy between two parse trees of target sentences. In order to calculate the lexical semantic similarity, it incorporates context-based word sense disambiguation producing synsets in WordNet as its outputs, which, in turn, can be transformed into more general ones. In experiments, we introduced two new parameters: tree kernel decay factors, and degrees of abstracting lexical concepts which can accelerate the optimization of PPI extraction performance in addition to the conventional SVM's regularization factor. Through these multi-strategic experiments, we confirmed the pivotal role of the newly applied parameters. Additionally, the experimental results showed that semantic parse tree kernel is superior to the conventional kernels especially in the PPI classification tasks.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.57-67
• /
• 2021

Recently, multi-modal deep learning techniques that combine heterogeneous data for deep learning analysis have been utilized a lot. In particular, studies on the synthesis of Text to Image that automatically generate images from text are being actively conducted. Deep learning for image synthesis requires a vast amount of data consisting of pairs of images and text describing the image. Therefore, various data augmentation techniques have been devised to generate a large amount of data from small data. A number of text augmentation techniques based on synonym replacement have been proposed so far. However, these techniques have a common limitation in that there is a possibility of generating a incorrect text from the content of an image when replacing the synonym for a noun word. In this study, we propose a text augmentation method to replace words using word hierarchy information for noun words. Additionally, we performed experiments using MSCOCO data in order to evaluate the performance of the proposed methodology.

• Journal of the Korea Society for Simulation
• /
• v.15 no.3
• /
• pp.115-124
• /
• 2006

XML is rapidly becoming technologies for information exchange and representation. It causes many research issues such as semantic modeling methods, security, conversion far interoperability with other models, and so on. Especially, the most important issue for its practical application is how to achieve the interoperability between XML model and relational model. Until now, many suggestions have been proposed to achieve it. However several problems still remain. Most of all, the exiting methods do not consider implicit referential integrity relations, and it causes incorrect data delivery. One method to do this has been proposed with the restriction where one semantic is defined as only one same name in a given database. In real database world, this restriction cannot provide the application and extensibility. This paper proposes a noble conversion (RDB-to-XML) algorithm based on the similarity checking technique. The key point of our method is how to find implicit referential integrity relations between different field names presenting one same semantic. To resolve it, we define an enhanced implicity referentiai integrity relations extraction algorithm based on a widely used ontology, WordNet. The proposed conversion algorithm is more practical than the previous-similar approach.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2006.06a
• /
• pp.237-244
• /
• 2006

시맨틱 웹 관련연구가 증가함에 따라 하나의 관련분야로 규칙기반 시스템 동의 지능적인 웹 환경에 대한 기대 역시 커지고 있다. 하지만 규칙기반 시스템을 활용하기에는 아직도 규칙습득이 많은 제약이 되고 있다. 규칙습득은 웹으로부터 필요한 규칙을 습득하는 일련의 방법인데, 이러한 규칙을 습득하기 위해서는 규칙구성요소를 먼저 식별해야만 한다. 그러나 이러한 규칙을 식별하는 작업은 대부분 지식관리자의 수작업에 의해 이루어지고 있다. 본 연구의 목적은 웹으로부터 규칙구성요소 식별을 최대한 자동화하고 지식관리자의 수작업을 최소화함으로써 그 부담을 줄여 주는 데 있다. 이러한 방법으로는 온톨로지를 근간으로 하여 웹 페이지와의 문자열 비교, 이러한 비교의 한계를 극복하기 위한 확장등의 방법이 있다. 첫 번째 방법은 온툴로지 기반으로 규칙식별 할 웹 페이지와 비교를 통해 지식관리자의 규칙식별 과정을 최대한 자동화하여 주는 것이다. 여기서 만약 현재 규칙을 식별하고자 하는 웹 사이트와 유사한 시스템의 규칙들을 활용하여 일반화 된 온툴로지가 구축되었다면, 이 온톨로지를 기반으로 규칙을 식별하고자 하는 웹사이트와의 비교를 통해 규칙구성요소를 자동화하여 추출 할 수 있다. 이러한 온툴로지를 기반으로 규칙을 식별하기 위해서는 문자열 비교 기법을 사용하게 된다. 하지만 단순한 문자열 비교 기법만으로는 규칙을 식별하는 데에 자연어 처리에 대한 한계가 있다. 이를 극복하기 위해 다음의 두 번째 방법을 사용하고자 한다. 두 번째 방법은 정형화되지 않은 정보들을 확장하여 사용하는 것이다. 우선 찾고자 하는 단어들의 원형을 찾기 위한 스테밍 알고리즘 기법, WordNet을 이용하여 동의어 유의어등으로 확장을 하는 WordNet Expansion 기법, 의미 유사도를 측정하기 위한 방법인 Semantic Similarity Measure 등을 단계적으로 수행하여 자동화되고 정확한 규칙식별을 하고자 한다. 이러한 방법들의 조합으로 인하여 규칙구성요소 추출이 되지 않을 후보 단어들의 수를 줄여서 보다 더 정확하고, 지능적인 규칙구성요소 추출 방법론을 제시하고 구현하여 지식관리자의 규칙습득에 대한 부담을 줄여 주고자 한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.2
• /
• pp.690-696
• /
• 2016

Search engines that rely on morphological matching of user query and web document content do not support individual interests. This research proposes a personalized web search scheme that returns the results that reflect the users' query intent and personal preferences. The performance of the personalized search depends on using an effective user profiling strategy to accurately capture the users' personal interests. In this study, the user profiles are the databases of topic words and customized weights based on the recent user queries and the frequency of topic words in click history. To determine the precise meaning of ambiguous queries and topic words, this strategy uses WordNet to calculate the semantic relatedness to words in the user profile. The experiments were conducted by installing a query expansion and re-ranking modules on the general web search systems. The results showed that this method has 92% precision and 82% recall in the top 10 search results, proving the enhanced performance.

• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.231-240
• /
• 2011

Many search algorithms have been implemented by many researchers on the world wide web. One of the best algorithms is Google using PageRank technology. PageRank approach computes the number of inlink of each documents then ranks documents in the order of inlink members. But it is difficult to find the results that user needs, because this method find documents not valueable for a person but valueable for the public. To solve this problem, We use the WordNet for analysis of the user's query history. This paper proposes a personalized search engine using the user's query history and PageRank Check. We compared the performance of the proposed approaches with google search results in the top 30. As a result, the average of the r-precision for the proposed approaches is about 60% and it is better as about 14%.

• Journal of Korean Library and Information Science Society
• /
• v.53 no.3
• /
• pp.169-191
• /
• 2022

The purpose of this study is to attempt a text network analysis for two years of 『Reference Materials for Librarian』 (2016-2017) published by the Library Operation Methodology Research Institute in North Korea. A text network analysis can measure how important a particular word by grasping the connectivity and relationship between words beyond a simple word frequency analysis, and it is also possible to interpret specific social phenomena and derive implications. Frequency, degree centrality, the betweenness centrality, community analysis of the collected words were calculated using NetMiner. As a result, the terms 'users', 'information services', 'information needs', 'information technology', 'social learning', 'computers', 'databases', 'information acquisition', 'information retrieval' and 'librarian' were appeared as important ones in understanding North Korean libraries.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.8
• /
• pp.727-739
• /
• 2003

In this paper, we propose a generation method of regression classes for adaptation in the HM-Net (Hidden Markov Network) system. The MLLR (Maximum Likelihood Linear Regression) adaptation approach is applied to the HM-Net speech recognition system for expressing the characteristics of speaker effectively and the use of HM-Net in various tasks. For the state level sharing, the context domain state splitting of PDT-SSS (Phonetic Decision Tree-based Successive State Splitting) algorithm, which has the contextual and time domain clustering, is adopted. In each state of contextual domain, the desired phoneme classes are determined by splitting the context information (classes) including target speaker's speech data. The number of adaptation parameters, such as means and variances, is autonomously controlled by contextual domain state splitting of PDT-SSS, depending on the context information and the amount of adaptation utterances from a new speaker. The experiments are performed to verify the effectiveness of the proposed method on the KLE (The center for Korean Language Engineering) 452 data and YNU (Yeungnam Dniv) 200 data. The experimental results show that the accuracies of phone, word, and sentence recognition system increased by 34∼37%, 9%, and 20%, respectively, Compared with performance according to the length of adaptation utterances, the performance are also significantly improved even in short adaptation utterances. Therefore, we can argue that the proposed regression class method is well applied to HM-Net speech recognition system employing MLLR speaker adaptation.

• Language and Information
• /
• v.15 no.2
• /
• pp.23-45
• /
• 2011

This paper proposes a statistical-based linguistic methodology for automatic mapping between large-scale heterogeneous languages resources for NLP applications in general. As a particular case, it treats automatic mapping between two large-scale heterogeneous Korean language resources: Sejong Semantic Classes (SJSC) in the Sejong Electronic Dictionary (SJD) and nouns in KorLex. KorLex is a large-scale Korean WordNet, but it lacks syntactic information. SJD contains refined semantic-syntactic information, with semantic labels depending on SJSC, but the list of its entry words is much smaller than that of KorLex. The goal of our study is to build a rich language resource by integrating useful information within SJD into KorLex. In this paper, we use both linguistic and statistical methods for constructing an automatic mapping methodology. The linguistic aspect of the methodology focuses on the following three linguistic clues: monosemy/polysemy of word forms, instances (example words), and semantically related words. The statistical aspect of the methodology uses the three statistical formulae ${\chi}^2$, Mutual Information and Information Gain to obtain candidate synsets. Compared with the performance of manual mapping, the automatic mapping based on our proposed statistical linguistic methods shows good performance rates in terms of correctness, specifically giving recall 0.838, precision 0.718, and F1 0.774.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.189-193
• /
• 2007

개념 간의 유사도 측정 방법은 의미망에서의 두 개념의 최단 경로의 수 노드의 깊이 관계의 종류 등의 정보를 이용하는 링크(Link) 기반 방법, 대용량의 말뭉치에서의 개념의 발생빈도를 확률로 계산한 정보량(Information Content) 기반 방법, 관련 단어들의 공기정보를 활용한 의미(Gloss) 기반 방법이 있으며, 이미 국외에서는 WordNet과 같은 의미적 언어자원을 활용하여 많은 연구가 진행되고 있다. 그러나 국내에서는 아직 한국어 의미망을 바탕으로 한 개념간의 유사성 측정 방법이나 이를 활용하는 방법에 대한 연구가 미흡하다. 본 논문에서는 이를 바탕으로 링크 타입 노드의 깊이 최단경로 정보량 등의 요소를 이용한 의미 유사도 측정방법을 제안하고 이를 활용하여 명사-용언간의 연계 정보를 확보함으로써, 효율적으로 명사-용언간의 네트워크를 구축하도록 한다.