• Language and Information
• /
• v.8 no.2
• /
• pp.47-72
• /
• 2004

In general, it is assumed that a pronoun refers to the same individual as the referent of its antecedent. However, when a pronoun and its antecedent are in different information or belief states, the two may not refer to the same individual. Then a question arises what a pronoun refers to. In this paper, two cases are considered. When a pronoun occurs in an attitude context, one case is where its antecedent occurs in a belief context, and the other is where the antecedent occurs in the main context. I propose that a pronoun refers to an individual concept which links two different subjects in two different contexts, and that the selection of a proper individual concept is restricted by the discourse. So a pronoun can be used felicitously only when there is a unique individual concept supported by the individual concept introduced by the discourse and which can link two subjects in two different contexts.

• Language and Information
• /
• v.5 no.2
• /
• pp.9-20
• /
• 2001

Barker (1997) has argued that all the three approaches to anaphora, namely, E-type theories, Discourse Representation Theory, and Dynamic Semantics, are faced with the so-called 'double-bind' problem in the quantifier/variable-binding model of anaphora. Recently, in the same journal, Slater (2000) has claimed that the so-called epsilon account (Slater 1991, 1993, 1994, 1997) handles the problem without any difficulty. However, it will be proposed in this paper that the epsilon account has its own problems in handling the quantifier/variable-binding, and that as argued in Yoon (1998), the so-called‘conjunctive paraphrase’account is the correct solution to the problem, which is intuitively supported as well.

• Annual Conference on Human and Language Technology
• /
• 2004.10d
• /
• pp.283-289
• /
• 2004

조응어 해석(Anaphora Resolution)은 여러 응용 분야에 적절히 적용됨으로써 자연어 이해에서의 양적. 질적 향상을 가져 올 수 있다. 구어에서 조응어(anaphor)는 화자와 청자간에 공유된 정보를 간략하게 나타내는 형태이다. 특히, 구어를 주된 사용 언어로 하는 대화 시스템에서의 조응어의 양상을 살피고 해석하는 문제는 인간과 기계간의 의사소통(man-machine communication)을 온전히 하는 과제이다. 이 논문에서는 인간과 기계간의 대화 시스템(man-machine dialogue system)에서 흔히 쓰일 수 있는 조응 표현에 중점을 두어 그 유형을 살피고 해석의 방식을 제시하도록 한다.

• Annual Conference on Human and Language Technology
• /
• 2002.10e
• /
• pp.317-324
• /
• 2002

참조현상이란 이미 언급되었던 혹은 이미 알고 있다고 여겨지는 정보에 대한 재표현이다. 참조현상은 자연언어처리 분야에서뿐만 아니라 인지과학, 심리학, 철학분야에서도 활발하게 연구되는 현상으로 참조표현인 조응사(anaphora)의 선행사(antecedent)를 채택하는 방법에 따라 그 성능이 좌우된다. 자연언어문장으로부터 멀티동화를 생성을 위한 애니메이션 제어 스크립트 명령들에서의 참조해결은 선행 정보의 적절한 참조를 바탕으로 자연스러운 애니메이션 장면을 생성하는데 있어서 필수적이다. 본 논문에서는 이러한 동화의 자연언어 문장에 나타나는 참조현상들에 대해 살펴보고 결합범주문법을 이용하여 참조현상을 해결하는 방법과 구현방법에 대해 논의한다.

• Language and Information
• /
• v.6 no.1
• /
• pp.91-103
• /
• 2002

The temporal structure of events on the discourse level has long been of great interest in both theoretical and computational linguistics. In this paper, we offer a unified approach to the temporal relationships related to a hierarchical discourse structure. We apply the method of pronoun resolution to the interpretation of tense. It is based on an analysis within the framework of the controlled information packaging theory. A unique aspect of our account is that temporal interpretation across discourse segments in global discourse is subject to the same principles as the interpretation of global anaphora, and that there is thus no need to postulate independent principles to account for the discourse behaviour of tense. In this way, we can neatly explain the general view that tense parallels the anaphoric nature of pronouns.

• Language and Information
• /
• v.6 no.2
• /
• pp.83-104
• /
• 2002

I argue that Definiteness Effect (DE) should include Indefiniteness Restriction (IR) as well as Definiteness Restriction (DR). DR is exhibited by existential constructions, predicate nominals, inalienable possession constructions, and verbs with semantic features like 〔((CAUSE TO) COME TO) EXIST〕. IR is caused by some existence presupposition of aspectual adverbs, aspectual verbs, repetitives, and topic markers. The environments for DR and IR determine the (in)definiteness of Korean bare noun phrases which otherwise can be used either way. The neutralization of DR is also induced by focus which imposes a certain amount of structure on the event quantification. Van der Sandt's (1992) Presuppositions-as- Anaphora-Theory is effectively used to account for those examples from DR, ID, and the neutralization of BR.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 1996.02a
• /
• pp.21-30
• /
• 1996

• The KIPS Transactions:PartB
• /
• v.17B no.3
• /
• pp.255-262
• /
• 2010

When a system is developed, requirements document is generated by requirement analysts and then translated to formal specifications by specifiers. If a formal specification can be generated automatically from a natural language requirements document, system development cost and system fault from experts' misunderstanding will be decreased. A pronoun can be classified in personal and demonstrative pronoun. In the characteristics of requirements document, the personal pronouns are almost not occurred, so we focused on the decision of antecedent for a demonstrative pronoun. For the higher accuracy in analysis of requirements document automatically, finding antecedent of demonstrative pronoun is very important for elicitation of formal requirements automatically from natural language requirements document via natural language processing. The final goal of this research is to automatically generate formal specifications from natural language requirements document. For this, this paper, based on previous research [3], proposes an anaphora resolution system to decide antecedent of pronoun using natural language processing from natural language requirements document in Korean. This paper proposes heuristic rules for the system implementation. By experiments, we got 92.45%, 69.98% as recall and precision respectively with ten requirements documents.

• Language and Information
• /
• v.10 no.2
• /
• pp.21-45
• /
• 2006

Connectivity effects have been central issues in dealing with specificational pseudoclefts. While syntactic approaches motivate their analysis in order to explain connectivity effects in terms of a connected clause, these accounts have numerous problems including a wide range of anti-connectivity effects that constitute crucial counterevidence. On the other hand, semantic accounts of connectivity effects treat BV and BT connectivity by independent interpretive mechanisms providing a more fundamental explanation for connectivity effects. Yet existing semantic accounts have limitations in explaining syntactic properties and syntactic connectivity effects in SPCs, and in accounting for BV anti-connectivity effects in English. Focusing on BV connectivity, this paper explores how the relevant (anti-)connectivity facts can be accounted for by an analysis that provides both an elaborate syntactic analysis of SPCs and a semantic mechanism for bound anaphora. Based on Yoo's (2005) non-deletion based, question-answer pair analysis of SPCs, this paper shows that a functional question analysis of a specificational subject, when combined with a theory of operator scope and a non-configurational condition on bound anaphora, can explain various BV (anti-)connectivity patterns in SPCs and related constructions.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.591-594
• /
• 2020

담화에서 의미를 전달하는 데 문제가 없을 경우에는 문장성분을 생략하여 표현한다. 생략된 문장성분을 무형대용어(zero anaphora)라고 한다. 무형대용어를 복원하기 위해서는 무형대용어 탐지와 무형대용어 해결이 필요하다. 무형대용어 탐지란 문장 내에서 생략된 필수성분을 찾는 것이고, 무형대용어 해결이란 무형대용어에 알맞은 문장성분을 찾아내는 것이다. 본 논문에서는 담화에서의 무형대용어 탐지 및 해결을 위한 말뭉치 생성 방법을 제안한다. 먼저 기존의 세종 구어 말뭉치에서 어휘지도를 이용하여 무형대용어를 복원한다. 이를 위해 본 논문에서는 동형이의어 부착과 어휘지도를 이용해서 무형대용어를 복원하고 복원된 무형대용어에 대한 오류를 수정하고 그 선행어(antecedent)를 수동으로 결정함으로써 무형대용어 해결 말뭉치를 생성한다. 총 58,896 문장에서 126,720개의 무형대용어를 복원하였으며, 약 90%의 정확률을 보였다. 앞으로 심층학습 등의 방법을 활용하여 성능을 개선할 계획이다.