• Journal of KIISE
• /
• v.44 no.8
• /
• pp.813-821
• /
• 2017

Entity Linking find the meaning of an entity mention, which indicate the entity using different expressions, in a user's query by linking the entity mention and the entity in the knowledge base. This task has four challenges, including the difficult knowledge base construction problem, multiple presentation of the entity mention, ambiguity of entity linking, and NIL entity recognition. In this paper, we first construct the entity name dictionary based on Wikipedia to build a knowledge base and solve the multiple presentation problem. We then propose various methods for NIL entity recognition and solve the ambiguity of entity linking by training the support vector machine based on several features, including the similarity of the context, semantic relevance, clue word score, named entity type similarity of the mansion, entity name matching score, and object popularity score. We sequentially use the proposed two methods based on the constructed knowledge base, to obtain the good performance in the entity linking. In the result of the experiment, our system achieved 83.66% and 90.81% F1 score, which is the performance of the NIL entity recognition to solve the ambiguity of the entity linking.

• Journal of KIISE
• /
• v.43 no.9
• /
• pp.1043-1051
• /
• 2016

Web based entity linking cannot be applied in tweet entity linking because twitter documents are shorter in comparison to web documents. Therefore, tweet entity linking uses the information of users or groups. However, data sparseness problem is occurred due to the users with the inadequate number of twitter experience data; in addition, a negative impact on the accuracy of the linking result for users is possible when using the information of unrelated groups. To solve the data sparseness problem, we consider three features including the meanings from single tweets, the users' own tweet set and the sets of other users' tweets. Furthermore, we improve the performance and the accuracy of the tweet entity linking by assigning a weight to the information of users with a high similarity. Through a comparative experiment using actual twitter data, we verify that the proposed tweet entity linking has higher performance and accuracy than existing methods, and has a correlation with solving the data sparseness problem and improved linking accuracy for use of information of high similarity users.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.3
• /
• pp.129-136
• /
• 2019

There are a variety of entities in natural language such as people, organizations, places, and products. These entities can have many various meanings. The ambiguity of entity is a very challenging task in the field of natural language processing. Entity Linking(EL) is the task of linking the entity in the text to the appropriate entity in the knowledge base. Pairwise based approach, which is a representative method for solving the EL, is a method of solving the EL by using the association between two entities in a sentence. This method considers only the interdependence between entities appearing in the same sentence, and thus has a limitation of global interdependence. In this paper, we developed an Entity2vec model that uses Word2vec based on knowledge base of RDF type in order to solve the EL. And we applied the algorithms using the generated model and ranked each entity. In this paper, to overcome the limitations of a pairwise approach, we devised a pairwise approach based on comprehensive interdependency and compared it.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.2
• /
• pp.111-118
• /
• 2015

Entity linking is to link entity's name mentions occurring in text to corresponding entities within knowledge bases. Since the same entity mention may refer to different entities according to their context, entity linking needs to deal with entity disambiguation. Most recent works on entity disambiguation focus on semantic relatedness between entities and attempt to integrate semantic relatedness with entity prior probabilities and term co-occurrence. To the best of my knowledge, however, it is hard to find studies that analyze and present the pure effects of semantic relatedness on entity disambiguation. From the experimentation on Korean Wikipedia data set, this article empirically evaluates entity disambiguation approaches using semantic relatedness in terms of the following aspects: (1) the difference among semantic relatedness measures such as NGD, PMI, Jaccard, Dice, Simpson, (2) the influence of ambiguities in co-occurring entity mentions' set, and (3) the difference between individual and collective disambiguation approaches.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.223-226
• /
• 2020

엔터티 링킹을 위해서는 엔터티 링킹을 수행 할 후보 엔터티의 정보를 얻어내는 것이 필요하다. 하지만, 엔터티 정보를 획득하기 어려운 경우, 엔터티 링킹을 수행 할 수 없다. 이 논문에서는 이를 해결하기 위해 데이터셋으로부터 엔터티의 가상 엔터티 설명문을 작성하고, 이를 통해 엔터티 링킹을 수행함으로써 엔터티 정보가 없는 환경에서도 2.58%p밖에 성능 하락이 일어나지 않음을 보인다.

• Journal of Computing Science and Engineering
• /
• v.8 no.3
• /
• pp.137-148
• /
• 2014

Named entity classification of Wikipedia articles is a fundamental research area that can be used to automatically build large-scale corpora of named entity recognition or to support other entity processing, such as entity linking, as auxiliary tasks. This paper describes a method of classifying named entities in Chinese Wikipedia with fine-grained types. We considered multi-faceted information in Chinese Wikipedia to construct four feature sets, designed different feature selection methods for each feature, and fused different features with a vector space using different strategies. Experimental results show that the explored feature sets and their combination can effectively improve the performance of named entity classification.

• Korean Journal of Cognitive Science
• /
• v.26 no.4
• /
• pp.435-452
• /
• 2015

Recent researches on Entity Linking(EL) have attempted to disambiguate entities by using a knowledge base to handle the semantic relatedness and up-to-date information. However, EL for tweets using a knowledge base is still unsatisfactory, mainly because the tweet data are mostly composed of short and noisy contexts and real-time issues. The EL system the present work builds up links ambiguous entities to the corresponding entries in a given knowledge base via exploring the news articles and the user history. Using news articles, the system can overcome the problem of Wikipedia coverage (i.e., not handling real-time issues). In addition, given that users usually post tweets related to their particular interests, the current system referring to the user history robustly and effectively works with a small size of tweet data. In this paper, we propose an approach to building an EL system that links ambiguous entities to the corresponding entries in a given knowledge base through the news articles and the user history. We created a dataset of Korean tweets including ambiguous entities randomly selected from the extracted tweets over a seven-day period and evaluated the system using this dataset. We use accuracy index(number of correct answer given by system/number of data set) The experimental results show that our system achieves a accuracy of 67.7% and outperforms the EL methods that exclusively use a knowledge base.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.128-131
• /
• 2020

엔터티 링킹은 주어진 문서 상에서 엔터티가 내포된 부분에 어떤 엔터티가 연결되어야 하는 지를 판단하는 작업이다. 따라서, 이 과정에서 엔터티의 표상을 얻어내는 것이 엔터티 링킹의 성능에 큰 영향을 끼치게 된다. 이 논문에서는 RELIC을 통해 엔터티 임베딩을 얻어내고, 이를 엔터티 링킹에 적용시킨 결과 0.57%p의 성능 향상을 이루었다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.20-23
• /
• 2020

개체 연결이란 문서에서 등장한 멘션(Mention)들을 지식 기반(Knowledge Base)상의 하나의 개체에 연결하는 문제를 말한다. 개체 연결은 개체를 찾는 멘션 탐지(mention detection)과정과 인식된 멘션에 대해 중의성을 해결하여 하나의 개체를 찾는 개체 중의성 해결(Entity disambiguation)과정으로 구성된다. 본 논문에서는 개체 정보를 강화하기 위해 wikipedia2vec정보를 결합하여 Entity 정보를 강화하고 문장 내에 모든 개체 정보를 활용하기 위해 집합적 개체를 정의하고 그래프 구조를 표현하기 위해 GNN을 활용하여 기존보다 높은 성능을 이끌어내었다.

• Genomics & Informatics
• /
• v.17 no.2
• /
• pp.20.1-20.5
• /
• 2019

Entity normalization, or entity linking in the general domain, is an information extraction task that aims to annotate/bind multiple words/expressions in raw text with semantic references, such as concepts of an ontology. An ontology consists minimally of a formally organized vocabulary or hierarchy of terms, which captures knowledge of a domain. Presently, machine-learning methods, often coupled with distributional representations, achieve good performance. However, these require large training datasets, which are not always available, especially for tasks in specialized domains. CONTES (CONcept-TErm System) is a supervised method that addresses entity normalization with ontology concepts using small training datasets. CONTES has some limitations, such as it does not scale well with very large ontologies, it tends to overgeneralize predictions, and it lacks valid representations for the out-of-vocabulary words. Here, we propose to assess different methods to reduce the dimensionality in the representation of the ontology. We also propose to calibrate parameters in order to make the predictions more accurate, and to address the problem of out-of-vocabulary words, with a specific method.