• The Journal of Society for e-Business Studies
• /
• v.26 no.3
• /
• pp.67-80
• /
• 2021

The node embedding technique for learning graph representation plays an important role in obtaining good quality results in graph mining. Until now, representative node embedding techniques have been studied for homogeneous graphs, and thus it is difficult to learn knowledge graphs with unique meanings for each edge. To resolve this problem, the conventional Triple2Vec technique builds an embedding model by learning a triple graph having a node pair and an edge of the knowledge graph as one node. However, the Triple2 Vec embedding model has limitations in improving performance because it calculates the relationship between triple nodes as a simple measure. Therefore, this paper proposes a feature extraction technique based on a graph convolutional neural network to improve the Triple2Vec embedding model. The proposed method extracts the neighborliness vector of the triple graph and learns the relationship between neighboring nodes for each node in the triple graph. We proves that the embedding model applying the proposed method is superior to the existing Triple2Vec model through category classification experiments using DBLP, DBpedia, and IMDB datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.11
• /
• pp.2903-2923
• /
• 2023

Knowledge recommendation is a type of recommendation system that recommends knowledge content to users in order to satisfy their needs. Although using graph neural networks to extract data features is an effective method for solving the recommendation problem, there is information loss when modeling real-world problems because an edge in a graph structure can only be associated with two nodes. Because one super-edge in the hypergraph structure can be connected with several nodes and the effectiveness of knowledge graph for knowledge expression, a dual-channel hypergraph convolutional neural network model (DCHC) based on hypergraph structure and knowledge graph is proposed. The model divides user data and knowledge data into user subhypergraph and knowledge subhypergraph, respectively, and extracts user data features by dual-channel hypergraph convolution and knowledge data features by combining with knowledge graph technology, and finally generates recommendation results based on the obtained user embedding and knowledge embedding. The performance of DCHC model is higher than the comparative model under AUC and F1 evaluation indicators, comparative experiments with the baseline also demonstrate the validity of DCHC model.

• Journal of Korea Multimedia Society
• /
• v.25 no.3
• /
• pp.493-501
• /
• 2022

This paper is a study on context-sensitive spelling error correction and uses the Korean WordNet (KorLex)[1] that defines the relationship between words as a graph to improve the performance of the correction[2] based on the vector information of the word embedded in the correction technique. The Korean WordNet replaced WordNet[3] developed at Princeton University in the United States and was additionally constructed for Korean. In order to learn a semantic network in graph form or to use it for learned vector information, it is necessary to transform it into a vector form by embedding learning. For transformation, we list the nodes (limited number) in a line format like a sentence in a graph in the form of a network before the training input. One of the learning techniques that use this strategy is Deepwalk[4]. DeepWalk is used to learn graphs between words in the Korean WordNet. The graph embedding information is used in concatenation with the word vector information of the learned language model for correction, and the final correction word is determined by the cosine distance value between the vectors. In this paper, In order to test whether the information of graph embedding affects the improvement of the performance of context- sensitive spelling error correction, a confused word pair was constructed and tested from the perspective of Word Sense Disambiguation(WSD). In the experimental results, the average correction performance of all confused word pairs was improved by 2.24% compared to the baseline correction performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.3
• /
• pp.91-100
• /
• 2020

Unlike the existing Visual Question Answering(VQA) problems, the new Visual Commonsense Reasoning(VCR) problems require deep common sense reasoning for answering questions: recognizing specific relationship between two objects in the image, presenting the rationale of the answer. In this paper, we propose a novel deep neural network model, KG_VCR, for VCR problems. In addition to make use of visual relations and contextual information between objects extracted from input data (images, natural language questions, and response lists), the KG_VCR also utilizes commonsense knowledge embedding extracted from an external knowledge base called ConceptNet. Specifically the proposed model employs a Graph Convolutional Neural Network(GCN) module to obtain commonsense knowledge embedding from the retrieved ConceptNet knowledge graph. By conducting a series of experiments with the VCR benchmark dataset, we show that the proposed KG_VCR model outperforms both the state of the art(SOTA) VQA model and the R2C VCR model.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.519-521
• /
• 2023

온라인 뉴스 플랫폼의 발전은 에코 챔버(echo chamber) 효과와 정치적 양극화를 심화시키며, 이를 완화하기 위한 선행 연구로 뉴스 기사의 정치적 성향을 판단하는 연구가 필요하다. 기존 연구는 외부 지식 그래프를 활용하여 뉴스 기사의 텍스트 정보를 더욱 풍부하게 표현한다. 그러나, 외부 지식을 임베딩하는 지식 그래프 임베딩(knowledge graph embedding, KGE) 방법은 다양하며, 각 KGE 방법이 정치적 성향 예측 정확도에 미치는 효과에 대해서 충분히 연구되지 않았다. 본 논문에서는 정치적 성향 예측에 외부 지식의 활용을 최대화하기 위한 다양한 KGE 방법들의 효과를 분석한다. 실험 결과, 외부 지식 그래프 내의 개체들 간 복잡한 관계를 간단하고 정확하게 표현 가능한 ModE 방법을 활용하는 것이 정치적 성향 예측에 가장 효과적이라는 것을 확인하였다.

• International journal of advanced smart convergence
• /
• v.12 no.3
• /
• pp.75-88
• /
• 2023

In a specific domain, experts have different understanding of domain knowledge or different purpose of constructing ontology. These will lead to multiple different ontologies in the domain. This phenomenon is called the ontology heterogeneity. For research fields that require cross-ontology operations such as knowledge fusion and knowledge reasoning, the ontology heterogeneity has caused certain difficulties for research. In this paper, we propose a novel ontology matching model that combines word embedding and a concatenated continuous bag-of-words model. Our goal is to improve word vectors and distinguish the semantic similarity and descriptive associations. Moreover, we make the most of textual and structural information from the ontology and external resources. We represent the ontology as a graph and use the SimRank algorithm to calculate the structural similarity. Our approach employs a similarity queue to achieve one-to-many matching results which provide a wider range of insights for subsequent mining and analysis. This enhances and refines the methodology used in ontology matching.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.272-275
• /
• 2019

단어 중의성 해소 방법은 지식 정보를 활용하여 문제를 해결하는 지식 기반 방법과 각종 기계학습 모델을 이용하여 문제를 해결하는 지도학습 방법이 있다. 지도학습 방법은 높은 성능을 보이지만 대량의 정제된 학습 데이터가 필요하다. 반대로 지식 기반 방법은 대량의 정제된 학습데이터는 필요없지만 높은 성능을 기대할수 없다. 최근에는 이러한 문제를 보완하기 위해 지식내에 있는 정보와 정제된 학습데이터를 기계학습 모델에 학습하여 단어 중의성 해소 방법을 해결하고 있다. 가장 많이 활용하고 있는 지식 정보는 상위어(Hypernym)와 하위어(Hyponym), 동의어(Synonym)가 가지는 의미설명(Gloss)정보이다. 이 정보의 표상을 기존의 문장의 표상과 같이 활용하여 중의성 단어가 가지는 의미를 파악한다. 하지만 정확한 문장의 표상을 얻기 위해서는 단어의 표상을 잘 만들어줘야 하는데 기존의 방법론들은 모두 문장내의 문맥정보만을 파악하여 표현하였기 때문에 정확한 의미를 반영하는데 한계가 있었다. 본 논문에서는 의미정보와 문맥정보를 담은 단어의 표상정보를 만들기 위해 구문정보, 의미관계 그래프정보를 GCN(Graph Convolutional Network)를 활용하여 임베딩을 표현하였고, 기존의 모델에 반영하여 문맥정보만을 활용한 단어 표상보다 높은 성능을 보였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.164-167
• /
• 2021

최근 구글, 아마존, LOD 등을 중심으로 지식 그래프(Knowledge graph)와 같은 검색 고도화 연구가 활발히 수행되고 있다.그러나 대규모 지식 그래프 인덱싱 시스템에서 데이터가 어떻게 임베딩(embedding)되고, 딥러닝(deep learning) 되는지는 상대적으로 거의 연구가 되지 않고 있다. 이에 본 논문에서는 임베딩 모델에 대한 성능평가를 통해 데이터셋에 대해 어떤 모델이 가장 좋은 지식 임베딩 방법을 도출하는지 분석한다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.5
• /
• pp.801-808
• /
• 2022

Research on how to embed knowledge in large-scale Linked Data and apply neural network models for entity matching is relatively scarce. The most fundamental problem with this is that different labels lead to lexical heterogeneity. In this paper, we propose an extended GCN (Graph Convolutional Network) model that combines re-align structure to solve this lexical heterogeneity problem. The proposed model improved the performance by 53% and 40%, respectively, compared to the existing embedded-based MTransE and BootEA models, and improved the performance by 5.1% compared to the GCN-based RDGCN model.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.174-177
• /
• 2015

자가 지식 학습 프레임워크는 자연어 텍스트에서 지식 트리플을 생성하기 위한 방법 중 하나로, 문장의 의존 관계 트리 상에서 주어 개체와 목적어 개체 사이의 관계를 패턴으로 학습해 이 패턴을 바탕으로 새로운 지식 트리플을 생성한다. 그러나 이 방법은 의존 관계 트리를 생성하는 도구의 성능에 영향을 받을 뿐만 아니라 생성된 지식 트리플을 반복적으로 사용하는 자가 지식 학습의 특성상 오류가 누적될 가능성이 있다. 이러한 문제점을 해결하기 위해서 본 논문에서는 자가 지식 학습 프레임워크에서 생성된 지식 트리플을 TransR 신뢰도 함수를 사용해 신뢰도 값을 측정하여 그 값에 따라 지식 트리플을 필터링하는 방법을 제안한다. 실험 결과에 따르면 필터링 된 지식 트리플들이 그렇지 않은 지식 트리플들에 비하여 더 높은 정확률을 보여주어, 제안한 방법이 자가 지식 학습 프레임워크의 정확률 향상에 효과적임을 증명하였다.