• Annual Conference on Human and Language Technology
• /
• 2004.10d
• /
• pp.323-328
• /
• 2004

The main concern of the paper is to establish a hypothesis in which the form thi is treated as a particular Contrastive Topic marker in Vietnamese sentence structure. We have investigated that the form thican be placed after a topical nominal or verbal to compose a Contrastive Topic phrase. Not only the subjects or objects but predicates in Vietnamese can have a CT interpretation with the marker thi. The thi-phrase not only refers to an entity or event the speaker wants to talk about, but also indicates that there exist contrastive alternatives the speaker wants to talk about. The nature of the contrastive topic decides the nature the alternative set and the choice of the topic of the implicated proposition. When the set of alternatives does not have the characteristic of scale, we have a descriptive opposite implicature. Again, if the contrastive set is a scalar set, we gat a denial-of expectation implicature.

• Korean Journal of Child Studies
• /
• v.18 no.2
• /
• pp.73-85
• /
• 1997

The purpose of the present study was to examine the role of semantic and syntactic knowledge in the first language acquisition of Korean classifiers. The elicited classifiers production test(EPT) was conducted to 105 children aged from 2 to 7. EPT consisted of 16 classifiers and two items for each classifier. 32 items were divided into 2 major semantic features: animacy and inanimacy. The semantic features of inanimacy were subcategorized into 3 features such as neutral, shape and function. The results revealed that; 1) children produced the correct structure of classification from the very early age with correct word order of the noun phrase showing early fundamental syntactic knowledge; 2) The earliest response pattern was to respond to all nouns in the same way using a neutral classifier showing no apparent semantic basis for their choice; 3) Children didn't show any preference for animate, shape, or function classifiers.

• Speech Sciences
• /
• v.11 no.4
• /
• pp.43-52
• /
• 2004

Model parameters in HMM based speech recognition systems are normally estimated using Maximum Likelihood Estimation(MLE). The MLE method is based mainly on the principle of statistical data fitting in terms of increasing the HMM likelihood. The optimality of this training criterion is conditioned on the availability of infinite amount of training data and the correct choice of model. However, in practice, neither of these conditions is satisfied. In this paper, we propose a training algorithm, MCE(Minimum Classification Error), to improve the performance of a speech recognizer detecting mispronunciation of a foreign language. During the conventional MLE(Maximum Likelihood Estimation) training, the model parameters are adjusted to increase the likelihood of the word strings corresponding to the training utterances without taking account of the probability of other possible word strings. In contrast to MLE, the MCE training scheme takes account of possible competing word hypotheses and tries to reduce the probability of incorrect hypotheses. The discriminant training method using MCE shows better recognition results than the MLE method does.

• Korean Journal of English Language and Linguistics
• /
• v.4 no.2
• /
• pp.195-227
• /
• 2004

This paper concerns the issue related to the focus phenomena with a particular reference to the two alternating orders (continuous vs. discontinuous orders) in particle constructions in English. To explain the alternation of word order in particle constructions, I will argue that the choice of word order is closely related to the focus property of the object DPs. Following Drubig (2003), I will assume that focus-feature is taken to be a syntactic feature assigned freely to a lexical head in the process of the mapping into Lexical Array (LA) from the lexicon (LEX). I argue that the focus-marked object DP cannot move out of its focus domain and thus the continuous order is derived. In the case of non-focus-marked object DP, however, the object DP moves out of VP in order to receive an appropriate interpretation. As a result, the discontinuous order is derived.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.190-193
• /
• 2015

이 논문에서는 한국의 수능 시험에 대응하는 일본 센터 시험의 세계사B 문제를 해결하는 시스템을 만들고 그 성능을 평가했다. 이 시스템은 문제의 각 보기의 신뢰도를 검증하여 어떤 보기가 참인지를 결정한다. 보기 검증을 위해 지식 베이스 기반, 정보 검색 기반, 시간적 제약 기반 검증을 사용하였다. 성능 평과 결과 6개년도 시험 중 5개 시험에서 통계적으로 의미 있는 결과를 얻었다. 이 시스템은 영어를 대상으로 하나, 한국어에도 존재하는 리소스를 사용했기 때문에 한국어에서도 같은 방법론을 적용할 수 있을 것으로 본다. 후속 연구로는 보기의 의미적 분석과 개체명 이외의 정보에 대한 검색이 필요하다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.53-56
• /
• 2014

Application specific instruction-set processor (ASIP) is a suitable design choice for system designers who seek both flexibility to handle various applications in the domain together with the performance. Successful development of an ASIP, however, requires a software development kit (SDK) to be provided along with the processor. Synopsys Processor Designer is an ASIP development tool, which takes as input a set of files written in a high-level architecture description language called LISA (Language for Instruction Set Architecture), and generates SDK as well as RTL. Recently, they have added support for the generation of LLVM compiler backend, though some manual work is required. In this paper, we introduce some details in porting LLVM compiler to a custom processor architecture in Synopsys Processor Designer.

• 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.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.53-56
• /
• 2008

The digital multimedia era has come and almost everyone creates and publishes multimedia contents over the internet. When the available amount of multimedia content is exponentially increasing, searching through the sea of the multimedia content is a big problem. In this paper, we present MPEG Query Format (MPQF), which is a new standard for multimedia query language based on XML-schema. MPQF provides a standardized interface for users of heterogeneous multimedia information service providers to access their services of choice in a homogeneous way.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.556-559
• /
• 2002

The Call Processing Language (CPL, in short), recommended in RFC 2824 of IETF, is a service description language for the Internet Telephony. The CPL allows users to define their own services, which dramatically improves the choice and flexibility of the users. The syntax of the CPL is strictly defined by DTD (Document Type Definition). However, compliance with the DTD is not a sufficient condition for correctness of a CPL script. There are enough rooms for non-expert users to make semantical mistakes in the service logic, which could lead to serious system down. In this paper, we present six classes of semantic warnings for the CPL service description: MF, IS, CR, AS, US, OS. For each class, we give the definition and its effects with an example script. These warnings are not necessarily errors. However, these warnings will help users to find ambiguity, redundancy and inconsistency in their own service description.

• Child Studies in Asia-Pacific Contexts
• /
• v.2 no.2
• /
• pp.91-107
• /
• 2012

This study aimed to understand communicative and socialization practices of immigrant bilingual families in everyday learning situations by examining interactions between parents and children in the United States. Drawn on language socialization theory and socio-cultural factors influencing immigrants, this study explored how three Korean American mothers struggled as they helped their children with homework by interviewing the mothers and observing mother-child interaction during homework time. The study paid attention to the emotional values of immigrant parents that they tried to teach their children who are members in two distinctive communities, such as Korean American and mainstream American. The findings showed that parental socialization practices had effects on children's emotional and social competence and at the same time the socialization process was bidirectional. Mothers started with Korean values, but they faced challenges with the English language, different demands for American homework, and children's rejection of their attempts. Mothers needed to change their strategy and borrow American ways of keeping emotional distance from their children by acknowledging their independence. Their struggles are discussed with attention to their language choice and culture.