• Annual Conference on Human and Language Technology
• /
• 2009.10a
• /
• pp.197-201
• /
• 2009

이 논문은 영어 문장에서 대명사의 참조해소 시스템을 구현한다. 대명사는 문장에서 반복되는 말 대신에 사용하는 단어이다. 반복되는 말을 선행어라고 하며 대명사는 선행어보다 간결한 형식으로 사용된다. 정보검색이나 정보추출에서 대명사를 그대로 색인하여 검색하면 정확한 정보를 추출할 수 없다. 따라서 대용어가 가리키는 개체를 정확히 파악해서 이 정보를 색인하고 검색하면 정보검색, 정보추출, 질의응답의 성능을 크게 개선할 수 있다. 이 논문에서는 CRF모델을 이용해서 이용하여 영어 문서에서 대명사 참조해결 방법을 제안하고 이를 구현한다.

• Annual Conference on Human and Language Technology
• /
• 2011.10a
• /
• pp.98-101
• /
• 2011

이 논문은 한-영 대화체 번역 시스템에서 영형 대명사 해소를 위한 새로운 방법론을 제시하였다. 영형 대명사는 문맥, 상황, 세상 지식으로부터 추론될 수 있는 문장에서 생략된 요소이다. 이 논문은 특히 주어-대명사 생략 현상에 대해 다루고 있는데, 그 이유는 드라마 대본이나 인스턴트 메신저 채팅과 같은 한국어 대화체에서는 매우 일반적인 현상이기 때문이다. 이 논문에서 우리는 많은 양의 지식을 요구하지 않는 간단한 방법론을 제시하였다. 평가결과 우리의 방법은 0.79의 F-measure 스코어를 달성하였고, 전체번역률의 측면에서는 약 4.1% 정도의 향상효과가 있었다.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.12
• /
• pp.873-880
• /
• 2013

This paper approaches the problem of resolving Korean zero pronouns using Centering Theory modeling local coherence. Centering Theory has been widely used to resolve English pronouns. However, it is much difficult to apply the centering framework for zero pronoun resolution in languages such as Japanese and Korean. Since in particular the use of non-anaphoric zero pronouns without explicit antecedents is not considered in the Centering Theory of Grosz et al., the presence of non-anaphoric cases negatively affects the performance of the resolution system based on Centering Theory. To overcome this, this paper presents a method which determines the intra-sentential anaphoricity of zero pronouns in subject position by using relationships between clauses, and then identifies antecedents of zero subjects. In our experiments, the proposed method outperforms the baseline method relying solely on Centering Theory.

• Korean Journal of Cognitive Science
• /
• v.18 no.1
• /
• pp.35-56
• /
• 2007

The English language has developed from a language with optional subjecthood Into a language with obligatory subjecthood due to a general reduction of inflections. Two types of subject omission, pro-drop and conjunction reduction, have been reported in the history of English. Old English with rich inflections had both referential pro-drop and conjunction reduction. Middle English with much lesser inflections still witnessed pro-drop and conjunction reduction, but in such a decreasing way that modern English with a loss of inflections developed from Middle English hardly has either pro-drop or conjunction reduction. This paper explores both the phenomena relating to optional subjecthood in Old, Middle, and Modern English in light of the cognitive processes of the universal, hierarchical constraints that are assumed to be inherent in English speakers' cognitive fatuity. It is found that optional subjecthood in Old, Middle, and Modern English is correctly raptured in terms of the distinct rankings of the proposed constraints, and that it is closely related to whether each of Old, Middle, and Modern English has rich inflections.

• Journal of Digital Convergence
• /
• v.12 no.12
• /
• pp.529-535
• /
• 2014

This study is to establish the consistency of Subject-Verb agreement in quantifier phrase. Absence of consistency in English grammar is critical to the grammaticality. We focused on the grammar part, specifically, S-V agreement rule in quantifier phrase. We believe the existence of exceptional rules in quantifier S-V structure is not necessary as the basic grammar rule on S-V agreement is sufficient enough and adding exceptional rules just make it more difficult and confusing. We argue specific features indwelt in each quantifier are linked when quantifiers are used pronominally and the ${\pm}$feature plays an important role in quantifier S-V agreement structure. This study shows the solution to eliminate the ungrammaticality in typical English text books by simplifying quantifier S-V agreement to make it solid and systematic.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2000.05a
• /
• pp.121-127
• /
• 2000

지금까지 상호 표현(reciprocal expressions)이나 상호성(reciprocity)의 개념에 대한 연구는 영어의 'each other'를 중심으로 이뤄졌다. 그런데 한국어의 상호 대명사 '서로'는 'each other'와 달리, 그 자체로 배분성(distributivity)을 갖지 않는다. 오히려 다양한 배분 표현들과 공기함으로써 상호성을 구체화한다. 특히, 배분적 양화사는 상호 표현이 쓰인 문장에 강한 상호성(strong reciprocity)을 부여한다. 이외에도 한국어의 상호성 실현에는 함께 쓰인 술어가 중요한 역할을 한다. 우선, 술어가 대칭적(symmetric)이거나, 상호 대명사(reciprocal)'서로'를 논항으로 취하면, 문장은 일차적으로 상호성을 갖게된다. 또한, 술어가 반가법(anti-additive)함수로서의 의미 특성을 갖는 경우는, 논항이 복수 연접 명사구로 구성되었을 때, 논항을 그룹(group)으로 해석하는 것을 선호한다. 본고는 상호성 술어(reciprocated predicates)와 배분적 양화사의 의미 기여를 중심으로, 한국어 상호 표현의 다양한 의미·통사적 특징을 밝히는 것을 목표로 하며, 이를 통해 상호성의 개념이 고정적이거나 문맥에 따라, 임의로 정해지는 무질서한 것이 아니라, 함께 쓰인 배분적 양화사나 술어의 의미 특성에 따라 합성적으로(compositionally) 실현되는 것임을 보이고자 하였다.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.313-323
• /
• 2021

The purpose of this study is to propose rules that can identify the speaker referred by the speaker directive in the text for the realization of a machine learning-based virtual character using a literary text. Through previous studies, we found that when applying literary texts to machine learning, the machine did not properly discriminate the speaker without any specific rules for the analysis of speaker directives such as other names, nicknames, pronouns, and so on. As a way to solve this problem, this study proposes 'nine rules for finding a speaker indicated by speaker directives (including pronouns)': location, distance, pronouns, preparatory subject/preparatory object, quotations, number of speakers, non-characters directives, word compound form, dispersion of speaker names. In order to utilize characters within a literary text as virtual ones, the learning text must be presented in a machine-comprehensible way. We expect that the rules suggested in this study will reduce trial and error that may occur when using literary texts for machine learning, and enable smooth learning to produce qualitatively excellent learning results.

• Annual Conference on Human and Language Technology
• /
• 1995.10a
• /
• pp.300-309
• /
• 1995

언어표현에 대한 해석은 그 구성요소들의 통사적-어휘적 구조에 덧붙여 대명사의 동일지시를 살펴야 할 필요가 있다. 조응의 분석과 조응적 선행사를 찾기 위한 효과적인 방법을 발견하는 것이 컴퓨터 언어학(computational linguistics), 특히 자연언어 이해체계(Natural Language understanding system)에 관한 연구의 중심적인 문제라고 할 수 있다. 이 논문의 목적은 영어 조응표현을 개념구조 이론(Conceptual Structure Theory)의 개념도식(conceptual graph)에 의하여 기술함으로써 단문에서뿐만 아니라 복문, 양화구문, 그리고 담화에 이르기까지 언어 전반에 걸쳐 나타나는 동일지시성(coreferenciality)을 간단하고 일관성 있게 설명하는 것이다. 이러한 조응현상을 설명하기 위하여 필자는 개념도식상의 개념을 중심개념, 직접개념, 간접개념으로 구분하고 이들이 문맥깊이 등과 더불어 동일지시성을 설명하는데 중심적 역할을 함을 보이고자 한다.

• English Language & Literature Teaching
• /
• no.6
• /
• pp.199-217
• /
• 2000

Relative pronoun that is one of the important relative pronouns but we have an impression that its scope of use has been somewhat narrowed. In the light of history of relative pronouns relative pronoun toot has the longest history of all relative pronouns and it was widely used even in Middle English and early Modem English. On The other hand, we can see that the relative use of that has been gradually weakened as the relative pronouns who and which has expanded their scope of use. It is quite natural that the scope of use of toot as a relative pronoun has been narrowed as who is mainly used in referring to person and which is mainly used in referring to things. And we can note that that is used only in restrictive clauses, not in nonrestrictive clauses, for that has a strong characteristics of relative conjunction in comparing with who and which. That as a relative pronoun still has its own weight because it can take an antecedent referring to person and thing. In particular, it is general tendency that who is used more frequently than that in the case of referring that it is not adequate for that to refer to things. In contrast, who has an advantage over that because the former originally refers only to person.

• The Journal of the Korea Contents Association
• /
• v.17 no.12
• /
• pp.378-385
• /
• 2017

The aim of this study was to analyze cohesion and word information among different types of questions in the English reading section of the College Scholastic Ability Tests (CSAT). The types of questions were divided into three categories: macro reading, micro reading, and indirect writing. Reading texts from 1994 to 2017 CSAT were analyzed by Coh-Metrix, an automated evaluation program of text and discourse. The findings of this study indicated that there were statistical differences among the three categories of questions for noun overlap, stem overlap, adversative and contrastive connective, additive connective, pronoun incidence, age of acquisition, concreteness for content word, imagability, and meaningfulness. The information of the findings bore pedagogic implications for developing textbooks, questions for CSAT, and reading strategies by students.