• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2005년도 하계 학술대회
• /
• pp.103-118
• /
• 2005

IT의 급격한 발전과 함께 새로운 형태의 정보 전달 방법이 지속적으로 나타나면서 우리말의 정확한 발음에 대한 인식이 점점 약화되고 있는 추세이다. 특히 장단음의 발음은 발화에 대한 전문인들도 정확하게 구분하지 못하고 있는 심각한 상황이다. 본 논문에서는 한국어 명사에서 나타나는 장단음화 현상을 주변 어휘와의 관계를 바탕으로 살펴보고 동음이의어 중 다르게 발음되는 명사의 장단음 구분을 명사와 명사의 수식어, 명사의 서술어와의 관계를 중심으로 논의한다. 분석된 결과는 결합범주문법을 이용하여 표현하고 어휘적 중의성이 해소된 음성 합성 과정을 표준화된 SSML(Speech Synthesis Markup Language)으로 기술한다.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2001년도 학술대회 논문집
• /
• pp.25-58
• /
• 2001

This study explores the lexical-semantic structure of derived causative verbs in Korean based on Pustejovsky(1995)'s Generative Lexicon Theory (GL), Mor-phological causative verbs are derived from their root stems by affixing ‘-i, -hi, -li, -gi’ in Korean and the meanings of derived predicates are closely related to the meanings of their root verbs. In particular, the change of the ARGUMENT STRUCTURE by morphological derivation leads to the change of the EVENT STRUCTURE. In this study, causation is defined as the cause-effect relation having a causer. The ARGUMENT STRUCTURES of derived causative verbs includes a causer argument, which is added to the ARGUMENT STRUCTURE of their root verbs. Their EVENT STRUCTURE has a headed process related to a causer and their result is the event which their root verbs represent. This approach can also suggest that the (in)directness of causative is determined by which verb is its root and explain the difference between the morphological causativization and the syntactic causativization in Korean.

• 한국언어정보학회지:언어와정보
• /
• 제5권1호
• /
• pp.35-53
• /
• 2001

As a subtype of English relative clause constructions, free relative constructions like what John ate in I ate what John ate exhibit complicated syntactic and semantic properties. In particular, the constructions have mixed properties of nominal and verbal: they have the internal syntax of sentence and the external syntax of noun phrase. This paper provides a constraint-based approach to these mixed constructions, and shows that simple constructional constraints are enough to capture their complexities. The paper begins by surveying the properties of the constructions. In discusses two types(Specific and nonspecific) of free relatives, their ,lexical restrictions nominal properties and behavior with respect to extraposition, piped piping and stacking Following these it sketches the basic framework of the HPSG(Head-driven Phrase Structure Grammar) which is of relevance in this paper. As the main part, the paper presents a constraint- based analysis in which tight interactions between grammatical constructions and a rich network of inheritance relations play important roles in accounting for the basic as well as complex properties of the constructions is question.

• 한국컴퓨터정보학회논문지
• /
• 제23권5호
• /
• pp.1-7
• /
• 2018

Reference string recognition is to extract individual reference strings from a reference section of an academic article, which consists of a sequence of reference lines. This task has been attacked by heuristic-based, clustering-based, classification-based approaches, exploiting lexical and layout characteristics of reference lines. Most classification-based methods have used sequence labeling to assign labels to either a sequence of tokens within reference lines, or a sequence of reference lines. Unlike the previous token-level sequence labeling approach, this study attempts to assign different labels to the beginning, intermediate and terminating tokens of a reference string. After that, post-processing is applied to identify reference strings by predicting their beginning and/or terminating tokens. Experimental evaluation using English and German reference string recognition datasets shows that the proposed method obtains above 94% in the macro-averaged F1.

• Journal of Information Processing Systems
• /
• 제8권2호
• /
• pp.301-314
• /
• 2012

In this paper, two new approaches to align English-Arabic sentences in bilingual parallel corpora based on the Multi-Class Support Vector Machine (MSVM) and the Hidden Markov Model (HMM) classifiers are presented. A feature vector is extracted from the text pair that is under consideration. This vector contains text features such as length, punctuation score, and cognate score values. A set of manually prepared training data was assigned to train the Multi-Class Support Vector Machine and Hidden Markov Model. Another set of data was used for testing. The results of the MSVM and HMM outperform the results of the length based approach. Moreover these new approaches are valid for any language pairs and are quite flexible since the feature vector may contain less, more, or different features, such as a lexical matching feature and Hanzi characters in Japanese-Chinese texts, than the ones used in the current research.

• 한국언어정보학회지:언어와정보
• /
• 제6권2호
• /
• pp.129-152
• /
• 2002

This paper argues for a need to adopt a conceptually radical approach to zero anaphora resolution in Korean. It is shown that a number of apparently conflicting constraints, mostly motivated by lexical, syntactic, semantic, and pragmatic factors, are involved in determining the referential identity of zero pronouns in Korean. It is also argued that some of the major concepts of Optimality Theory can provide a good theoretical framework to predict the antecedents to zero pronouns in general. A partial formalization of 07-based constraints at the morpho-syntactic and lexico-semantical level is provided. It is argued that the lexico-semantic restrictions on adjacent expressions play the most important role in the anaphora resolution process along with a variant of the binding principle, formulated in semantic terms. Other pragmatically motivated constraints that incorporate some important intuitions of Centering Theory are proposed too.

• 한국언어정보학회지:언어와정보
• /
• 제8권1호
• /
• 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.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2014년도 춘계학술발표대회
• /
• pp.745-748
• /
• 2014

SentiWordNet is an important lexical resource supporting sentiment analysis in opinion mining applications. In this paper, we propose a novel approach to construct a Vietnamese SentiWordNet (VSWN). SentiWordNet is typically generated from WordNet in which each synset has numerical scores to indicate its opinion polarities. Many previous studies obtained these scores by applying a machine learning method to WordNet. However, Vietnamese WordNet is not available unfortunately by the time of this paper. Therefore, we propose a method to construct VSWN from a Vietnamese dictionary, not from WordNet. We show the effectiveness of the proposed method by generating a VSWN with 39,561 synsets automatically. The method is experimentally tested with 266 synsets with aspect of positivity and negativity. It attains a competitive result compared with English SentiWordNet that is 0.066 and 0.052 differences for positivity and negativity sets respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권10호
• /
• pp.1698-1711
• /
• 2011

Knowledge is often represented as a set of rules or a semantic network in intelligent systems. Recently, ontology has been widely used to represent semantic knowledge, because it organizes thesaurus and hierarchal information between concepts in a particular domain. However, it is not easy to collect semantic relationships among concepts. Much time and expense are incurred in ontology construction. Collective intelligence can be a good alternative approach to solve these problems. In this paper, we propose a collective intelligence approach of Games With A Purpose (GWAP) to collect various semantic resources, such as words and word-senses. We detail how to construct the semantic information model or ontology from the collected semantic resources, constructing a system named FunWords. FunWords is a Korean lexical-based semantic resource collection tool. Experiments demonstrated the resources were grouped as common nouns, abstract nouns, adjective and neologism. Finally, we analyzed their characteristics, acquiring the semantic relationships noted above. Common nouns, with structural semantic relationships, such as hypernym and hyponym, are highlighted. Abstract nouns, with descriptive and characteristic semantic relationships, such as synonym and antonym are underlined. Adjectives, with such semantic relationships, as description and status, illustration - for example, color and sound - are expressed more. Last, neologism, with the semantic relationships, such as description and characteristics, are emphasized. Weighting the semantic relationships with these characteristics can help reduce time and cost, because it need not consider unnecessary or slightly related factors. This can improve the expressive power, such as readability, concentrating on the weighted characteristics. Our proposal to collect semantic resources from the collective intelligence approach of GWAP (our FunWords) and to weight their semantic relationship can help construct the semantic information model or ontology would be a more effective and expressive alternative.

• 한국차세대컴퓨팅학회논문지
• /
• 제13권2호
• /
• pp.102-110
• /
• 2017

최근 자연어 처리 분야에서 단어의 모호성을 해소하기 위해서 다양한 기계 학습 방법이 적용되고 있다. 지도 학습에 사용되는 데이터는 정답을 부착하기 위해 많은 비용과 시간이 필요하므로 최근 연구들은 비지도 학습의 성능을 높이기 위한 노력을 지속적으로 시도하고 있다. 단어 모호성 해소(word sense disambiguation)를 위한 비지도 학습연구는 지식 기반(knowledge base)를 이용한 방법들이 주목받고 있다. 이 방법은 학습 데이터 없이 지식 기반의 정보을 이용하여 문장 내에서 모호성을 가지는 단어의 의미를 결정한다. 지식 기반을 이용한 방법에는 그래프 기반방식과 유사도 기반 방법이 대표적이다. 그래프 기반 방법은 모호성을 가지는 단어와 그 단어가 가지는 다양한 의미들의 집합 간의 모든 경로에 대한 의미 그래프를 구축한다는 장점이 있지만 불필요한 의미 경로가 추가되어 오류를 증가시킨다는 단점이 있다. 이러한 문제를 해결하기 위해 본 논문에서는 그래프 구축을 위해 불필요한 간선들을 배제하면서 반복적으로 그래프를 재구축하는 모델을 제안한다. 또한, 구축된 의미 그래프에서 더욱 정확한 의미를 예측하기 위해 하이브리드 유사도 예측 모델을 적용한다. 또한 제안된 모델은 다국어 어휘 의미망 사전인 BabelNet을 사용하기 때문에 특정 언어뿐만 아니라 다양한 언어에도 적용 가능하다.