• 한국영어학회지:영어학
• /
• 제3권2호
• /
• pp.255-280
• /
• 2003

The present paper will argue what can be considered to be principled elements of the initial state S/sub 0/ of the Faculty of Language, which are called the Interface Condition (IC), and how far we can take the strongest minimalist thesis (SMT), which aims to offer principled explanation of language in terms of IC and the principle of efficient computation, to linguistic analysis. We will discuss implications of label-free phrase structures, required by the strong version of the Inclusiveness Condition, and possibilities of crash-free syntax, required by the condition of efficient computation. I will point out problems of Chomsky's assumption that an externally Merged expletive there is a head, which, as a probe, undergoes agreement with the goal T. I will present several advantages we obtain if we maintain A and A' distinction, and assume that wh-movement to the outer [SPEC, υ] is an A'-movement like wh-movement to [SPEC, C].

• 한국언어정보학회지:언어와정보
• /
• 제17권2호
• /
• pp.67-91
• /
• 2013

This paper describes Korean Nominal Bank, a project that provides argument structure for instances of the predicative nouns in the Sejong parsed Corpus. We use the language resources of the Sejong project, so that the same set of data is annotated with more and more levels of annotation, since a new type of a language resource building project could bring new information of separate and isolated processing. We have based on the annotation scheme based on the Sejong electronic dictionary, semantically tagged corpus, and syntactically analyzed corpus. Our work also involves the deep linguistic knowledge of syntaxsemantic interface in general. We consider the semantic theories including the Frame Semantics of Fillmore (1976), argument structure of Grimshaw (1990) and argument alternation of Levin (1993), and Levin and Rappaport Hovav (2005). Various syntactic theories should be needed in explaining various sentence types, including empty categories, raising, left (or right dislocation). We also need an explanation on the idiosyncratic lexical feature, such as collocation and etc.

• 한국영어학회지:영어학
• /
• 제2권2호
• /
• pp.207-226
• /
• 2002

In this paper we provide an alternative explanation for there construction, by assuming that the expletive there (EXPL) has independently uninterpretable Case feature as well as u[person], not as being pied-pipied with $\varphi$-feature. If EXPL has only u[person], we could analyse incorrectly some there constructions, including an embedded infinitive clause: by Chomsky (1998, 1999) in the construction, EXPL is ‘frozen’ and cannot participate in the computation of higher. As a result, we could predict incorrectly that the derivation is crashed. But if EXPL has two uninterpretable features, u[person] and u[Case], we could predict correctly that the derivation is converged: the u[person] of EXPL is deleted under Matching/Agree with $T_{def}$; still, the undeleted u[Case] of EXPL is activating; so EXPL can be raised to [SPEC, T] to satisfy the EPP-feature of matrix T.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권10호
• /
• pp.3230-3255
• /
• 2022

Causality mining in NLP is a significant area of interest, which benefits in many daily life applications, including decision making, business risk management, question answering, future event prediction, scenario generation, and information retrieval. Mining those causalities was a challenging and open problem for the prior non-statistical and statistical techniques using web sources that required hand-crafted linguistics patterns for feature engineering, which were subject to domain knowledge and required much human effort. Those studies overlooked implicit, ambiguous, and heterogeneous causality and focused on explicit causality mining. In contrast to statistical and non-statistical approaches, we present Bidirectional Encoder Representations from Transformers (BERT) integrated with Multi-level Feature Networks (MFN) for causality recognition, called BERT+MFN for causality recognition in noisy and informal web datasets without human-designed features. In our model, MFN consists of a three-column knowledge-oriented network (TC-KN), bi-LSTM, and Relation Network (RN) that mine causality information at the segment level. BERT captures semantic features at the word level. We perform experiments on Alternative Lexicalization (AltLexes) datasets. The experimental outcomes show that our model outperforms baseline causality and text mining techniques.

• 인지과학
• /
• 제21권4호
• /
• pp.669-696
• /
• 2010

본 논문은 한 문서의 전체 의미는 각 부분의미의 합성이라는 관점에서 미리 반자동으로 구축된 감정어휘 평가사전을 기반으로 한 시스템을 제안한다. 인간의 의사 결정 과정과 유사한 방식으로 의사 결정 과정을 모델링하려는 노력으로써 본 ARSSA 시스템은 개별 리뷰의 의미값 연산과 자료 분류를 통해 감정 표현이 나타난 영화평 리뷰의 자동 등급화에 대한 연구를 수행한다. 이는 {'평점' : '리뷰'} 이항구조로 이루어진 현재의 평점 부여 형식에서 발생하는 두 변항의 불연속성 문제를 해결해보려는 목적을 가진다. 이는 어휘 의미 합성 과정에서 반영된 추상적 의미들의 합성 함수를 통해 실현될 수 있다. 시스템의 성능 실험에서 네이버 무비에서 확보한 1000개의 리뷰에 대한 10-fold 교차 검증 실험이 수행되었다. 이 실험은 기존에 부여된 평점과 비교하여 감정어휘 평가사전을 이용하였을 때 85%의 F1 Score를 보였다.