• Language and Information
• /
• v.8 no.1
• /
• pp.77-100
• /
• 2004

This paper aims to account for direct combination of an entity type noun with the verb HA- 'do' (ex. piano-rul ha- 'piano-ACC do') in Korean, based on Generative Lexicon Theory (Pustejovsky, 1995). The verb HA-'do' coerces some entity type nouns (e.g., pap 'boiled rice') into event type ones, by virtue of the qualia of the nouns. Typically, a telic-based type coercion supplies individual predication to the HA- construction and an agentive-based type coercion evokes a stage-level interpretation. Type coercion has certain constraints on the choice of qualia. We further point out that qualia cannot be a warehouse of pragmatic information. Qualia are composed of necessary information to explain the lattice structure of lexical meaning and co-occurrence constraints, distinct from accidental information. Finally, we seriously consider co-composition as an alternative to type coercion for the crucial operation of type shift.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.7
• /
• pp.285-292
• /
• 2014

A named entity recognition method is used to improve the performance of information retrieval systems, question answering systems, machine translation systems and so on. The targets of the named entity recognition are usually PLOs (persons, locations and organizations). They are usually proper nouns or unregistered words, and traditional named entity recognizers use these characteristics to find out named entity candidates. The titles of books, movies and TV programs have different characteristics than PLO entities. They are sometimes multiple phrases, one sentence, or special characters. This makes it difficult to find the named entity candidates. In this paper we propose a method to quickly extract title named entities from news articles and automatically build a named entity dictionary for the titles. For the candidates identification, the word phrases enclosed with special symbols in a sentence are firstly extracted, and then verified by the SVM with using feature words and their distances. For the classification of the extracted title candidates, SVM is used with the mutual information of word contexts.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.247-251
• /
• 2018

상호참조해결은 자연언어 문서 내에서 등장하는 명사구 언급(mention)과 이에 선행하는 명사구 언급을 찾아 같은 개체인지 정의하는 문제이다. 특히, 지식베이스 확장에 있어 상호참조해결은 언급 후보에 대해 선행하는 개체의 언급이 있는지 판단해 지식트리플 획득에 도움을 준다. 영어권 상호참조해결에서는 F1 score 73%를 웃도는 좋은 성능을 내고 있으나, 평균 정밀도가 80%로 지식트리플 추출에 적용하기에는 무리가 있다. 따라서 본 논문에서는 한국어 문서에 대해 영어권 상호참조해결 모델에서 사용되었던 최신 모델인 Bi-LSTM 기반의 딥 러닝 기술을 구현하고 이에 더해 언급 후보 목록을 만들어 개체명 유형과 경계를 적용하였으며 품사형태를 붙인 토큰을 사용하였다. 실험 결과, 문자 임베딩(Character Embedding) 값을 사용한 경우 CoNLL F1-Score 63.25%를 기록하였고, 85.67%의 정밀도를 보였으며, 같은 모델에 문자 임베딩을 사용하지 않은 경우 CoNLL F1-Score 67.92%와 평균 정밀도 77.71%를 보였다.

• The KIPS Transactions:PartB
• /
• v.10B no.2
• /
• pp.229-236
• /
• 2003

Named entity recognition is the process indispensable to question answering and information extraction systems. This paper presents an HMM based named entity (m) recognition method using the construction principles of compound words. In Korean, many named entities can be decomposed into more than one word. Moreover, there are contextual relationships among nouns in an NE, and among an NE and its surrounding words. In this paper, we classify words into a word as an NE in itself, a word in an NE, and/or a word adjacent to an n, and train an HMM based on NE-related word types and parts of speech. Proposed named entity recognition (NER) system uses trigram model of HMM for considering variable length of NEs. However, the trigram model of HMM has a serious data sparseness problem. In order to solve the problem, we use multi-level back-offs. Experimental results show that our NER system can achieve an F-measure of 87.6% in the economic articles.

• Korean Journal of Cognitive Science
• /
• v.24 no.4
• /
• pp.301-321
• /
• 2013

For the task of sentence ordering, this paper attempts to utilize the Entity-Grid model, a type of entity-based modeling approach, as well as Latent Semantic analysis, which is based on vector space modeling, The task is well known as one of the fundamental tools used to measure text coherence and to enhance text generation processes. For the implementation of the Entity-Grid model, we attempt to use the syntactic roles of the nouns in the Korean text for the ordering task, and measure its impact on the result, since its contribution has been discussed in previous research. Contrary to the case of German, it shows a positive result. In order to obtain the information on the syntactic roles, we use a strategy of using Korean case-markers for the nouns. As a result, it is revealed that the cues can be helpful to measure text coherence. In addition, we compare the results with the ones of the LSA-based model, discussing the advantages and disadvantages of the models, and options for future studies.