• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.349-357
• /
• 2007

Named entities (NEs) are important in many Natural Language Processing (NLP) applications, and discovering NE-related relations in texts may be beneficial for these applications. This paper proposes a method to extract the ISA relation between a "named entity" and its category, and an IS-RELATED-TO relation between the category and its related object. Based on the pattern extraction algorithm "Person Category Extraction" (PCE), we extend it for solving our problem. Our experiments on Wall Street Journal (WSJ) corpus show promising results. We also demonstrate a possible application of these relations by utilizing them for semantic search.

• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1103-1125
• /
• 2017

This paper aims to extract an ObjectProperty-UsageMethod relation, in particular the HerbalMedicinalProperty-UsageMethod relation of the herb-plant object, as a semantic relation between two related sets, a herbal-medicinal-property concept set and a usage-method concept set from several web documents. This HerbalMedicinalProperty-UsageMethod relation benefits people by providing an alternative treatment/solution knowledge to health problems. The research includes three main problems: how to determine EDU (where EDU is an elementary discourse unit or a simple sentence/clause) with a medicinal-property/usage-method concept; how to determine the usage-method boundary; and how to determine the HerbalMedicinalProperty-UsageMethod relation between the two related sets. We propose using N-Word-Co on the verb phrase with the medicinal-property/usage-method concept to solve the first and second problems where the N-Word-Co size is determined by the learning of maximum entropy, support vector machine, and naïve Bayes. We also apply naïve Bayes to solve the third problem of determining the HerbalMedicinalProperty-UsageMethod relation with N-Word-Co elements as features. The research results can provide high precision in the HerbalMedicinalProperty-UsageMethod relation extraction.

• Journal of the Korean Society for Library and Information Science
• /
• v.50 no.2
• /
• pp.309-336
• /
• 2016

This paper introduces a relation extraction system that can be used in identifying and classifying semantic relations between biomedical entities in scientific texts using machine learning methods such as Support Vector Machines (SVM). The suggested system includes many useful functions capable of extracting various linguistic features from sentences having a pair of biomedical entities and applying them into training relation extraction models for maximizing their performance. Three globally representative collections in biomedical domains were used in the experiments which demonstrate its superiority in various biomedical domains. As a result, it is most likely that the intensive experimental study conducted in this paper will provide meaningful foundations for research on bio-text analysis based on machine learning.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.9-13
• /
• 2020

관계 추출은 주어진 문장이나 문서에 존재하는 개체들 간의 의미적 관계를 찾아내는 작업을 말한다. 최근 문서 수준 관계 추출 말뭉치인 DocRED가 공개되면서 문서 수준 관계 추출에 대한 연구가 활발히 진행되고 있다. 또한 사전 학습된 Masked Language Model(MLM)이 자연어처리 분야 전체에 영향력을 보이면서 관계 추출에서도 MLM을 사용하는 연구가 진행되고 있다. 그러나 문서 수준의 관계 추출은 문서의 단위가 길기 때문에 Self-attention을 기반으로 하는 MLM을 사용하면 모델의 계산량이 증가하는 문제가 있다. 본 논문은 이 점을 보완하기 위해 관계 추출에 필요한 문장을 선별하는 간단한 전처리 방법을 제안한다. 또한 문서의 길이에 상관없이 관계 추출에 필요한 어휘 정보를 자동으로 습득 할 수 있는 Relation-Context Co-attention 방법을 제안한다. 제안 모델은 DocRED 말뭉치에서 Dev F1 62.01%, Test F1 59.90%로 높은 성능을 보였다.

• KIISE Transactions on Computing Practices
• /
• v.23 no.3
• /
• pp.194-198
• /
• 2017

In this paper, we propose a revised Deep Convolutional Neural Network (DCNN) model to extract Protein-Protein Interaction (PPIs) from the scientific literature. The proposed method has the merit of improving performance by applying various global features in addition to the simple lexical features used in conventional relation extraction approaches. In the experiments using AIMed, which is the most famous collection used for PPI extraction, the proposed model shows state-of-the art scores (78.0 F-score) revealing the best performance so far in this domain. Also, the paper shows that, without conducting feature engineering using complicated language processing, convolutional neural networks with embedding can achieve superior PPIE performance.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.1
• /
• pp.93-114
• /
• 2023

Information extraction can facilitate the intensive analysis of documents by providing semantic triples which consist of named entities and their relations recognized in the texts. However, most of the research so far has been carried out separately for named entity recognition and relation extraction as individual studies, and as a result, the effective performance evaluation of the entire information extraction systems was not performed properly. This paper introduces two models of end-to-end information extraction that can extract various entity names in clinical records and their relationships in the form of semantic triples, namely pipeline and joint models and compares their performances in depth. The pipeline model consists of an entity recognition sub-system based on bidirectional GRU-CRFs and a relation extraction module using multiple encoding scheme, whereas the joint model was implemented with a single bidirectional GRU-CRFs equipped with multi-head labeling method. In the experiments using i2b2/VA 2010, the performance of the pipeline model was 5.5% (F-measure) higher. In addition, through a comparative experiment with existing state-of-the-art systems using large-scale neural language models and manually constructed features, the objective performance level of the end-to-end models implemented in this paper could be identified properly.

• Journal of KIISE
• /
• v.42 no.6
• /
• pp.817-822
• /
• 2015

Relation extraction is an important information extraction technique that can be widely used in areas such as question-answering and knowledge population. Previous studies on relation extraction have been based on supervised machine learning models that need a large amount of training data manually annotated with relation categories. Recently, to reduce the manual annotation efforts for constructing training data, distant supervision methods have been proposed. However, these methods suffer from a drawback: it is difficult to use these methods for collecting negative training data that are necessary for resolving classification problems. To overcome this drawback, we propose a one-class classification model that can be trained without using negative data. The proposed model determines whether an input data item is included in an inner category by using a similarity measure based on lexical information and syntactic patterns in a vector space. In the experiments conducted in this study, the proposed model showed higher performance (an F1-score of 0.6509 and an accuracy of 0.6833) than a representative one-class classification model, one-class SVM(Support Vector Machine).

• The Journal of the Korea Contents Association
• /
• v.10 no.2
• /
• pp.481-489
• /
• 2010

Due to the increase of the attention on relation extraction systems, the construction of test collections for assessing their performance has emerged as an important task. In this paper, we propose semi-automatic framework capable of constructing test collections for relation extraction on a large scale. Based on this framework, we develop a test collection which can assess the performance of various approaches to extracting relations between technical terminologies in scientific literatures. This framework can minimize the cost of constructing this kind of collections and reduce the intrinsic fluctuations which may come from the diversity in characteristics of collection developers. Furthermore, we can construct balanced and objective collections by means of controlling the selection process of seed documents and terminologies using the proposed framework.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.5
• /
• pp.1-10
• /
• 2007

Many types of information provided through the web including news contents contain unnecessary clutters. These clutters make it difficult to build automated information processing systems such as the summarization, extraction and retrieval of documents. We propose a system that extracts and summarizes news contents from the web. The extraction system receives news contents in HTML as input and builds an element tree similar to DOM tree, and extracts texts while removing clutters with the hyperlink attribute in the HTML tag from the element tree. Texts extracted through the extraction system are transferred to the summarization system, which extracts key sentences from the texts. We implement the summarization system using co-occurrence relation graph. The summarized sentences of this paper are expected to be transmissible to PDA or cellular phone by message services such as SMS.

• Journal of the Korean Society for Library and Information Science
• /
• v.51 no.4
• /
• pp.227-248
• /
• 2017

This paper introduces an integrated model for systematically constructing a linguistic resource database that can be used by machine learning-based biomedical information extraction systems. The proposed method suggests an orderly process of collecting and constructing dictionaries and training sets for both named-entity recognition and relation extraction. Multiple heterogeneous structures for the resources which are collected from diverse sources are analyzed to derive essential items and fields for constructing the integrated database. All the collected resources are converted and refined to build an integrated linguistic resource storage. In this paper, we constructed entity dictionaries of gene, protein, disease and drug, which are considered core linguistic elements or core named entities in the biomedical domains and conducted verification tests to measure their acceptability.