• Annual Conference on Human and Language Technology
• /
• 1994.11a
• /
• pp.177-180
• /
• 1994

영한 기계변역에서의 전치사구 처리는 자연어 처리의 중요한 연구과제 중 하나이다. 특히 전치사구의 격의미는 그에 대한 한국어 표현에 중요한 실마리가 된다. 본 논문은 영어의 전치사구에 대한 한국어 표현을 선택하기 위한 격의미 체계를 정의하고 그 격의미 체계를 실험한다. 이 격의미 체계는 전치사구에 대한 한국어의 격의미를 분별함으로 보다 좋은 한국어 격조사를 선택하게 해준다. 본 논문에서는 각 격의미의 구분을 위한 의미속성 집합도 정의한다. 이 의미속성 집합은 WordNet의 시소러스에서 제공한 상하위 관계와 변환표를 근거로 자동적으로 추출된다. 의미속성 집합의 자동획득은 격의미 체계의 표현과 기계변역의 성능 평가에 일반성을 부여한다. 격의미 체계와 의미속성 집합의 자동 획득은 영한 기계변역은 물론 한국어 생성과 자연어 처리에 중요한 기여를 할 것으로 보인다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.178-180
• /
• 2001

원시언어 문장의 구조 분석을 기반으로 하는 기계번역 시스템에서 원시언어의 최소 의미 단위는 동사를 중심으로 한 단문으로 생각할 수 있다. 단문 단위 대역어를 지정하기 위해서는 동사구 번역패턴의 사용이 요구된다. 본 논문에서는 한국어 단문 내 격 정보와 번역을 위한 의미 제약조건을 기술하여 한영 기계번역 시스템에서 사용하는 동사구 번역패턴을 정의하고, 문장 정규화를 통한 동사구 번역패턴의 활용방법을 제안한다. 동사구 번역패턴은 단문 구조 파악을 위한 제약 조건부와 대역어 선정부로 나뉜다. 제약 조건부는 단문 구조 번역을 위한 최소한의 의미 제약만으로 기술되며, 격조사로 구분되는 격 정보를 갖는다. 이러한 격 정보는 원시언어인 한국어의 단문 분석을 위해 사용되며 분석결과에 대해 단문 단위 대역어를 지정한다. 동사구 번역 패턴은 실제 말뭉치에서의 사용을 반영하기 위해 병렬 말뭉치로부터 구축되며 실험을 통해 예측되는 패턴의 규모를 알아볼 수 있다.

• Korean Educational Research Journal
• /
• v.39 no.1
• /
• pp.39-56
• /
• 2018

The purpose of this study is to examine the comparation Korean "-e(에), -eseo(에서)" with the Chinese "zai(在)," analyze the errors of using "-e(에), -eseo(에서)," and suggest the direction of teaching required for Chinese learners to reduce these errors. Referring to mean place, "-e(에)" and "-eseo(에서)" generally correspond to "zai(在)" in Chinese, but "zai(在)" in Chinese does not completely correspond to "-e(에)" and "-eseo(에서)" with the meaning of position or place. Chinese learners are often misunderstood when they use "-e(에)" and "-eseo(에서)."

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.4-6
• /
• 2006

본 논문은 자연언어처리에서 문장의 서술어와 그 서술어가 가지는 명사 논항들 사이의 문법관계를 의미 관계로 사상하는 즉 논항이 서술어에 대해 가지는 역할을 정하는 문제를 다루고 있다. 의미역 결정은 단어의 의미 중의성 해소와 함께 자연언어의 의미 분석의 핵심 문제 중 하나이며 반드시 해결해야 하는 매우 중요한 문제 중 하나이다. 본 연구에서는 언어학적으로 유용한 자원인 세종전자사전을 이용하여 용언격틀사전을 구축하고 격틀 선택 방법으로 의미역을 결정한 후. 결정된 의미역들에 대한 확률 정보를 확률 모델에 적용하여 반복적으로 학습하는 부트스트래핑(Bootstrapping) 알고리즘을 사용하였다. 실험 결과, 기본 모델에 대해 10% 정도의 성능 향상을 보였다.

• Journal of KIISE:Software and Applications
• /
• v.27 no.6
• /
• pp.668-677
• /
• 2000

Korean has the characteristics that case postpositions determine the syntactic roles of phrases and a postposition may have more than one meanings. In particular, the adverbial postpositions make translation from Korean to English difficult, because they can have various meanings. In this paper, we describe a method for resolving such semantic ambiguities of Korean adverbial postpositions using decision trees. The training examples for decision tree induction are extracted from a corpus consisting of 0.5 million words, and the semantic roles for adverbial postpositions are classified into 25 classes. The lack of training examples in decision tree induction is overcome by clustering words into classes using a greedy clustering algorithm. The cross validation results show that the presented method achieved 76.2% of precision on the average, which means 26.0% improvement over the method determining the semantic role of an adverbial postposition as the most frequently appearing role.

• Korean Journal of Cognitive Science
• /
• v.24 no.4
• /
• pp.301-321
• /
• 2013

For the task of sentence ordering, this paper attempts to utilize the Entity-Grid model, a type of entity-based modeling approach, as well as Latent Semantic analysis, which is based on vector space modeling, The task is well known as one of the fundamental tools used to measure text coherence and to enhance text generation processes. For the implementation of the Entity-Grid model, we attempt to use the syntactic roles of the nouns in the Korean text for the ordering task, and measure its impact on the result, since its contribution has been discussed in previous research. Contrary to the case of German, it shows a positive result. In order to obtain the information on the syntactic roles, we use a strategy of using Korean case-markers for the nouns. As a result, it is revealed that the cues can be helpful to measure text coherence. In addition, we compare the results with the ones of the LSA-based model, discussing the advantages and disadvantages of the models, and options for future studies.

• Korean Journal of Cognitive Science
• /
• v.20 no.4
• /
• pp.507-533
• /
• 2009

This paper examines the time course and processing patterns of filler-gap dependencies in Korean relative clauses, using an eyetracking method. Participants listened to a short story while viewing four pictures of entities mentioned in the story. Each story is followed by an auditorily presented question involving a relative clause (subject relative or dative relative). Participants' eye movements in response to the question were recorded. Results showed that the proportion of looks to the picture corresponding to a filler noun significantly increased at the relative verb affixed with a relativizer, and was largest at the filler where the fixation duration on the filler picture significantly increased. These results suggest that online resolution of the filler-gap dependency only starts at the relative verb marked with a relativiser and is finally completed at the filler position. Accordingly, they partly support the filler-driven parsing strategy for Korean, as for head-initial languages. In addition, the different patterns of eye movements between subject relatives and dative relatives indicate the role of case markers in parsing Korean sentences.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.6
• /
• pp.219-230
• /
• 2014

An analysis of dependency relation is a job that determines the governor and the dependent between words in sentence. The dependency relation of predicate is established by patterns and selectional restriction of subcategorization of the predicate. This paper proposes a method of analysis of Korean dependency relation using homograph predicate disambiguated in morphology analysis phase. The disambiguated homograph predicates has each different pattern. Especially reusing a stage transition training dictionary used during tagging POS and homograph, we propose a method of fixing the dependency relation of {noun+postposition, predicate}, and we analyze the accuracy and an effect of homograph for analysis of dependency relation. We used the Sejong Phrase Structured Corpus for experiment. We transformed the phrase structured corpus to dependency relation structure and tagged homograph. From the experiment, the accuracy of dependency relation by disambiguating homograph is 80.38%, the accuracy is increased by 0.42% compared with one of undisambiguated homograph. The Z-values in statistical hypothesis testing with significance level 1% is ${\mid}Z{\mid}=4.63{\geq}z_{0.01}=2.33$. So we can conclude that the homograph affects on analysis of dependency relation, and the stage transition training dictionary used in tagging POS and homograph affects 7.14% on the accuracy of dependency relation.

• (The)Study of the Eastern Classic
• /
• no.41
• /
• pp.407-444
• /
• 2010

So far, we morphologically considered which satirized society in the enlightenment period. For this, we first looked into the feature of expletive and then analyzed it centering around Declension. At last, we conclude this subject with argument of the creation time of from the morphological analysis result. Begining with the conclusion, I thought that the origin opinion of the creation time of is right. In priority research focusing on people who major in literature, the creation time of is about 1901 to 1907, and it coincide with the result from morphological consideration of this article. First, at the feature of expletive, the advent of '~ 할 말이면' the expression of the conditional mood helped to estimate the creation time of . Prior literature of the creation time of (around 1910), '~ 작시면' is the corresponding conditional mood expression. but in the new-style fiction around , it change to '~ 말이면' and thereafter '~ 것 갓흐면' or '~' which seems similar to present korean. I analized the record for the feature of expletive. By dividing up with merce miswrite and miswrite from ignorance, we can assume that the Scripter of is not the fictionist. At the feature of declension, the full use of the nominative case marker '-가' was recordable. '-가' had already appeared in early modern korean, but until 1883 '-ㅣ' almost replaced it. However, around period, we could know that '-ㅣ' barely used and mostly use '-가'. From this, I estimated the creation time of is at least after 1883. In conclusion, I want to suggest an opinion that 1900 is proper sectioning time when we divide history of korean to Modern and Present korean based on the discussion of this article.

• Journal of the Daesoon Academy of Sciences
• /
• v.49
• /
• pp.401-432
• /
• 2024

This article examines the types of "wind (바람)" accepted in sijo (three-verse poems), focusing on the accepted pattern, and investigating its role and meaning. The summary is as follows: first of all, the works of "wind" were accepted in the sijo, and the total number of works was 620. There were 459 short sijo, and 161 long sijo. On the other hand, 148 authors wrote on "The Wind," and in the Late Joseon Dynasty, 90 authors composed 265 poems, the most. In the Early Joseon Dynasty, 50 poets composed 111 poems. Most of them were civil officials, and 170 poems were identified. Next, the aspect of jang (章) was confirmed to occur 684 times in total, with 632 instances of being single uses and 52 instances of duplication. Meanwhile, the core of the sijo, the first sentence of the last chapter, contains 'wind (바람)' 34 times in 25 words. And in terms of the aspect of the particle combined with 'wind,' the nominative particle appeared the most at 113 instances, and the auxiliary particle 'eun/neun (은/는)' was the most numerous at 58 instances. As for the types of wind contained in sijo, there are 6 major categories: 106 medium categories, with the total frequency is 688. 'Singular' appears 133 times in 6 words, and 'combination' appears 121 times in terms of total frequency. The combination with terrestrial objects was the most frequent at 79 times, and the combination with 'heavenly' objects was 75 times with 3 words, and 'mixture' indicated a mixture of several objects, with 7 words occurring 42 times. Second the literary acceptance and role of 'wind' in Sijo was examined. First, 'acceptance' and the role as a medium for conveying ideas, acceptance and the role as the development of ideas, and acceptance and role of literary expression. Through this, it can be seen that 'wind' in Sijo was accepted in literature and played a major role. Lastly, the role and meaning of wind in Sijo can be seen in the fact that it remains differentiated from other form of ancient literature or other genres. It serves as a literary device that effectively expresses the theme, and the scope of the material accepted in Sijo was expanded through wind.