• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.415-421
• /
• 2007

This paper proposes a convolution tree kernel-based approach for relation extraction where the parse tree is expanded with entity features such as entity type, subtype, and mention level etc. Our study indicates that not only can our method effectively capture both syntactic structure and entity information of relation instances, but also can avoid the difficulty with tuning the parameters in composite kernels. We also demonstrate that predicate verb information can be used to further improve the performance, though its enhancement is limited. Evaluation on the ACE2004 benchmark corpus shows that our system slightly outperforms both the previous best-reported feature-based and kernel-based systems.

• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.642-652
• /
• 2009

In order to improve the performance of the existing relation extraction approaches, we propose a method for combining two pivotal concepts which play an important role in classifying semantic relationships between entities in text. Having built a composite kernel-based relation extraction system, which incorporates both entity features and syntactic structured information of relation instances, we define nine classes of lexical features and synthetically apply them to the system. Evaluation on the ACE RDC corpus shows that our approach boosts the effectiveness of the existing composite kernels in relation extraction. It also confirms that by integrating the three important features (entity features, syntactic structures and contextual lexical features), we can improve the performance of a relation extraction process.

• Journal of Internet Computing and Services
• /
• v.12 no.5
• /
• pp.73-85
• /
• 2011

Lots of valuable textual information is used to extract relations between named entities from literature. Composite kernel approach is proposed in this paper. The composite kernel approach calculates similarities based on the following information:(1) Phrase structure in convolution parse tree kernel that has shown encouraging results. (2) Predicate-argument structure patterns. In other words, the approach deals with syntactic structure as well as semantic structure using a reciprocal method. The proposed approach was evaluated using various types of test collections and it showed the better performance compared with those of previous approach using only information from syntactic structures. In addition, it showed the better performance than those of the state of the art approach.

• 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 KIISE:Computing Practices and Letters
• /
• v.15 no.12
• /
• pp.988-992
• /
• 2009

In this paper, we attempted to extract binary relations between terminologies using composite kernels consisting of convolution parse tree kernels and WordNet verb synset vector kernels which explain the semantic relationships between two entities in a sentence. In order to evaluate the performance of our system, we used three domain specific test collections. The experimental results demonstrate the superiority of our system in all the targeted collection. Especially, the increase in the effectiveness on KREC 2008, 8% in F1, shows that the core contexts around the entities play an important role in boosting the entire performance of relation extraction.

• Journal of KIISE:Software and Applications
• /
• v.37 no.2
• /
• pp.85-94
• /
• 2010

This paper introduces a novel way to leverage convolution parse tree kernel to extract the interaction information between two proteins in a sentence without multiple features, clues and complicated kernels. Our approach needs only the parse tree alone of a candidate sentence including pairs of protein names which is potential to have interaction information. The main contribution of this paper is two folds. First, we show that for the PPI, it is imperative to execute parse tree pruning removing unnecessary context information in deciding whether the current sentence imposes interaction information between proteins by comparing with the latest existing approaches' performance. Secondly, this paper presents that tree kernel decay factor can play an pivotal role in improving the extraction performance with the identical learning conditions. Consequently, we could witness that it is not always the case that multiple kernels with multiple parsers perform better than each kernels alone for PPI extraction, which has been argued in the previous research by presenting our out-performed experimental results compared to the two existing methods by 19.8% and 14% respectively.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.327-329
• /
• 2012

문서 내에 존재하는 중요한 개체들 간의 관계를 자동으로 추출할 때 개체와 개체 사이의 상호작용 표현에 중요하게 관여하는 핵심자질을 잘 선택할수록 빠르고 정확하게 관계 추출을 수행할 수 있다. 본 논문에서는 개체 쌍 사이에 존재하는 술어-논항 구조의 어휘 패턴 문자열을 정규화해서 스트링 커널에 적용하는 관계 추출 방법을 제안한다. 제안된 시스템의 성능 평가를 위해서 과학기술문헌에 존재하는 중요한 개체들 간의 연관관계 추출 성능 평가를 수행하는 테스트컬렉션을 자체적으로 구축하였으며 실험을 통하여 제안된 방법의 성능을 측정하였다. 정확도 실험 결과, 스트링 커널의 입력으로 문장 전체를 사용한 경우에는 55.0693%, 개체 쌍 사이의 문자열을 사용한 경우에는 61.0331%, 그리고 술어-논항 구조의 어휘 패턴 문자열을 사용한 경우에는 69.14%로, 술어-논항 구조의 어휘 패턴 문자열을 사용했을 때 성능이 가장 좋게 나타났다. 결론적으로 문장 내의 술어-논항 구조를 분석하여 정규화된 어휘 패턴을 생성하고 이렇게 생성된 문자열을 스트링 커널에 적용하는 방법이 관계 추출에 유용한 방법임을 알 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.276-279
• /
• 2011

문서 내에 존재하는 개체 간의 관계를 자동으로 추출할 때 다양한 형태의 문서 분석 결과를 활용할 수 있다. 본 논문에서는 기존에 개발되어 비교적 높은 성능을 보여준 트리 커널의 구절 구조 유사성 정보와 두 개체 사이의 유의미한 연관관계를 표현하는 술어-논항 구조 패턴의 유사성 정보를 활용하는 혼합 커널을 제안한다. 구문적 구조를 이용하는 기존의 트리 커널 기법에 술어와 논항 간의 의미적 구조를 활용하는 술어-논항 구조 패턴 유사도 커널을 결합하여 상호보완적인 혼합 커널을 구성하였고, 실험을 통하여 개발된 커널의 성능을 측정하였다. 실험 결과 구절 구조 정보를 이용하는 트리 커널만을 단독으로 사용했을 때보다 술어-논항 구조의 패턴 정보를 결합한 혼합 커널을 사용했을 때에 더 좋은 성능을 보이는 것을 확인할 수 있었다. 이는 관계 인스턴스에 대한 구절 구조 정보뿐만 아니라 개체 간의 유의미한 연관관계를 표현해주는 술어-논항 구조 패턴 또한 관계 추출 작업에 매우 유용한 정보임을 입증하고 있다.