• 한국항행학회논문지
• /
• 제20권6호
• /
• pp.617-624
• /
• 2016

한글 워드임베딩은 명사 추출과정을 거치지 않으면, 학습에 필요하지 않은 단어까지 학습하게 되어 효율적인 임베딩 결과를 도출할 수 없다. 본 연구는 한글 워드임베딩, 아프리오리, 텍스트 마이닝을 이용하여, 특정 도메인에서 질의어 확장에 의해 보다 효율적으로 답변을 검색할 수 있는 모델을 제안하였다. 워드임베딩과 아프리오리는 질의어에 대해서 의미와 맥락에 따라 연관 단어를 추출하여, 질의어를 확장하는 단계이다. 한글 텍스트 마이닝은 명사 추출, TF-IDF, 코사인 유사도를 이용하여, 유사답변 추출과 사용자에게 답변하는 단계이다. 제안모델은 특정 도메인의 답변을 학습하고, 연관성 높은 질의어를 확장함으로서 답변의 정확성을 높일 수 있다. 향후 연구과제로서, 데이터베이스에 저장된 사용자 질의를 분석하고, 보다 연관성 높은 질의어를 추출하는 연구가 필요하다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2006년도 춘계학술대회
• /
• pp.354-360
• /
• 2006

The purpose of this paper is to propose a securely personalized context-aware cooperative query that supports a multi-level data abstraction hierarchy and conceptual distance metric among data values, while considering privacy concerns around user context awareness. The conceptual distance expresses a semantic similarity among data values with a quantitative measure, and thus the conceptual distance enables query results to be ranked. To show the feasibility of the methodology proposed in this paper we have implemented a prototype system in the area of site search in a large-scale shopping mall.

• 정보처리학회논문지D
• /
• 제11D권2호
• /
• pp.269-280
• /
• 2004

피라미드 기법은 n-차원 공간 데이터를 1차원 데이터로 변환하여 B+-트리로 표현하며, n-차원 데이터 공간에서 하이퍼큐브 영역질의 처리로 발생하는 “차원의 저주현상”에 영향을 받지 않게 검색 시간 문제를 해결하고 있다. 또 구형 피라미드 기법(SPY-TEC)은 피라미드 기법의 공간 분할 전략을 응용하여 유사도 검색에 적합한 구 영역질의 방법을 사용하고 검색 성능을 개선하고 있다. 하지만 유사도 검색의 응용에서 영역질의는 범위를 지정하는데 어려움이 있어 최근접 질의가 더 효율적이며, 기존의 제안된 인덱스 기법들은 특정 분포의 데이터에 대해서만 우수한 성능을 보이는 단점이 있다. 따라서 이 논문에서는 멀티미디어 데이터와 같은 고차원 데이터의 검색 성능을 향상시키기 위해 제안되었던 PdR-트리를 이용하여 최근접 객체 검색 기법을 제안한다. 다양한 분포의 모의 데이터와 실제 데이터를 이용하여 실험한 결과, PdR-트리가 피라미드 기법과 구형 피라미드 기법보다 검색 성능이 향상되었음을 보이고 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1986-1989
• /
• 2003

This paper proposes the information retrieval improvement for the Web using the structure and hyperlinks of HTML documents along with user profile. The method bases on the rationale that terms appearing in different structure of documents may have different significance in identifying the documents. The method partitions the occurrence of terms in a document collection into six classes according to the tags in which particular terms occurred (such as Title, H1-H6 and Anchor). We use genetic algorithm to determine class importance values and expand user query. We also use this value in similarity computation and update user profile. Then a genetic algorithm is used again to select some terms from user profile to expand the original query. Lastly, the search engine uses the expanded query for searching and the results of the search engine are scored by similarity values between each result and the user profile. Vector space model is used and the weighting schemes of traditional information retrieval were extended to include class importance values. The tested results show that precision is up to 81.5%.

• Journal of Computing Science and Engineering
• /
• 제8권2호
• /
• pp.94-106
• /
• 2014

Schema matching is widely used in many applications, such as data integration, ontology merging, data warehouse and dataspaces. In this paper, we propose a novel matching technique that is based on the order of attributes appearing in the schema structure of query results. The appearance order embodies the extent of the importance of an attribute for the user examining the query results. The core idea of our approach is to collect statistics about the appearance order of attributes from the query logs, to find correspondences between attributes in the schemas to be matched. As a first step, we employ a matrix to structure the statistics around the appearance order of attributes. Then, two scoring functions are considered to measure the similarity of the collected statistics. Finally, a traditional algorithm is employed to find the mapping with the highest score. Furthermore, our approach can be seen as a complementary member to the family of the existing matchers, and can also be combined with them to obtain more accurate results. We validate our approach with an experimental study, the results of which demonstrate that our approach is effective, and has good performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권10호
• /
• pp.4987-5005
• /
• 2017

This paper introduces a new method to solve Similarity Recognition for Cloth Products, which is based on Fuzzy logic and Particle swarm optimization algorithm. For convenience, it is called the SRCPFP method hereafter. In this paper, the SRCPFP method combines Fuzzy Logic (FL) and Particle Swarm Optimization (PSO) algorithm to solve similarity recognition for cloth products. First, it establishes three features, length, thickness, and temperature resistance, respectively, for each cloth product. Subsequently, these three features are engaged to construct a Fuzzy Inference System (FIS) which can find out the similarity between a query cloth and each sampling cloth in the cloth database D. At the same time, the FIS integrated with the PSO algorithm can effectively search for near optimal parameters of membership functions in eight fuzzy rules of the FIS for the above similarities. Finally, experimental results represent that the SRCPFP method can realize a satisfying recognition performance and outperform other well-known methods for similarity recognition under considerations here.

• Journal of Information Processing Systems
• /
• 제15권6호
• /
• pp.1503-1516
• /
• 2019

In this paper, to improve the accuracy of long sentence similarity calculation, we proposed a sentence similarity calculation method based on a system similarity function. The algorithm uses word2vector as the system elements to calculate the sentence similarity. The higher accuracy of our algorithm is derived from two characteristics: one is the negative effect of penalty item, and the other is that sentence similar function (SSF) based on word2vector similar elements doesn't satisfy the exchange rule. In later studies, we found the time complexity of our algorithm depends on the process of calculating similar elements, so we build an index of potentially similar elements when training the word vector process. Finally, the experimental results show that our algorithm has higher accuracy than the word mover's distance (WMD), and has the least query time of three calculation methods of SSF.

• The Journal of the Acoustical Society of Korea
• /
• 제26권3E호
• /
• pp.69-73
• /
• 2007

This paper presents an efficient algorithm to retrieve similar music files from a large archive of digital music database. Users are able to navigate and discover new music files which sound similar to a given query music file by searching for the archive. Since most of the methods for finding similar music files from a large database requires on computing the distance between a given query music file and every music file in the database, they are very time-consuming procedures. By measuring the acoustic distance between the pre-classified music files with the same type of emotion, the proposed method significantly speeds up the search process and increases the precision in comparison with the brute-force method.

• 대한음성학회지:말소리
• /
• 제57호
• /
• pp.99-112
• /
• 2006

In this paper, we introduce two retrieval methods for photos with speech documents. We compare the pattern of speech query with those of speech documents recorded in digital cameras, and measure the similarities, and retrieve photos corresponding to the speech documents which have high similarity scores. As the first approach, a phoneme recognition scheme is used as the pre-processor for the pattern matching, and in the second one, the vector quantization (VQ) and the dynamic time warping (DTW) are applied to match the speech query with the documents in signal domain itself. Experimental results show that the performance of the first approach is highly dependent on that of phoneme recognition while the processing time is short. The second method provides a great improvement of performance. While the processing time is longer than that of the first method due to DTW, but we can reduce it by taking approximated methods.

• 한국정보처리학회논문지
• /
• 제7권7호
• /
• pp.2108-2115
• /
• 2000

The conventional Boolean retrieval systems based on vector spae model can provide the results of retrieval fast, they can't reflect exactly user's retrieval purpose including semantic information. Consequently, the results of retrieval process are very different from those users expected. This fact forces users to waste much time for finding expected documents among retrieved documents. In his paper, we designed a bayesian SOM(Self-Organizing feature Maps) in combination with bayesian statistical method and Kohonen network as a kind of unsupervised learning, then perform classifying documents depending on the semantic similarity to user query in real time. If it is difficult to observe statistical characteristics as there are less than 30 documents for clustering, the number of documents must be increased to at least 50. Also, to give high rank to the documents which is most similar to user query semantically among generalized classifications for generalized clusters, we find the similarity by means of Kohonen centroid of each document classification and adjust the secondary rank depending on the similarity.