• Title/Summary/Keyword: 어휘-의미장

Search Result 8, Processing Time 0.019 seconds

Valenztheoretische Untersuchung der deutschen Emotionsverben (결합가 이론에 의한 독일어 감정동사 연구)

  • Kim Soo-Nam
    • Koreanishche Zeitschrift fur Deutsche Sprachwissenschaft
    • /
    • v.6
    • /
    • pp.23-55
    • /
    • 2002
  • 이 논문의 목적은 수없이 많은 독일어 동사들 가운데 사람의 심리-감정을 표현하는 동사, 소위 감정동사(Emotionsverben: Verben der Gefuhlsbewegung)를 하나의 어휘-의미장(lexikalisch-semantisches Feld)으로 보고 이들의 통사구조 및 의미구조를 파악하여 결합가 모형화 하는 것이다. 우리는 감정동사의 통사 구조 및 의미구조를 기술하기 위해 동사 중심의 결합가 이론과 격이론을 이론적$\cdot$방법론적 토대로 삼았다. 또한 우리는 감정동사를 보충어의 수와 형태에 따라 크게 세 가지 그룹, 즉 2개의 보충어를 갖는 그룹 I(이 그룹에 속하는 동사들은 무생물(사물)을 주어로 갖는다)과 그룹 II(이 그룹에 속하는 동사들은 유생물(사람)을 주어로 갖는다) 그리고 3개의 보충어를 갖는 그룹 III(사람과 사람간의 관계를 나타낸다)으로 구분하였다. 예증을 위해 개별 동사에 대해 용례를 제시했다. 2개의 보충어를 갖는 그룹 II를 보충어의 수의성 여부에 따라 하위 분류했다. 보충어의 형태는 명사구(Sn, Sd, Sa, Sa)와 전치사구(pS)에 한정했으며 - 지면관계상 개별 동사의 예문으로 제시하진 않았지만 - 문장형태의 보충어, 예를 들어 dass-문장(Nsdass)과 부정사문(Inf)도 고려하여 통사적 문형(syntaktisches Satzmodell)과 의미적문형(semantisches Satzmodell)에서 제시하였다. 결국 이 논문은 독일어를 배우는 이들에게 독일어 동사의 통사구조 및 의미구조를 보다 쉽게 설명할 수 있는 하나의 방법론을 제시함은 물론, 나아가서는 결합가 사전에서 동사 내항 기술을 위한 기본적인 토대를 제공할 것이다

  • PDF

Korean Semantic Role Labeling Using Case Frame Dictionary and Subcategorization (격틀 사전과 하위 범주 정보를 이용한 한국어 의미역 결정)

  • Kim, Wan-Su;Ock, Cheol-Young
    • Journal of KIISE
    • /
    • v.43 no.12
    • /
    • pp.1376-1384
    • /
    • 2016
  • Computers require analytic and processing capability for all possibilities of human expression in order to process sentences like human beings. Linguistic information processing thus forms the initial basis. When analyzing a sentence syntactically, it is necessary to divide the sentence into components, find obligatory arguments focusing on predicates, identify the sentence core, and understand semantic relations between the arguments and predicates. In this study, the method applied a case frame dictionary based on The Korean Standard Dictionary of The National Institute of the Korean Language; in addition, we used a CRF Model that constructed subcategorization of predicates as featured in Korean Lexical Semantic Network (UWordMap) for semantic role labeling. Automatically tagged semantic roles based on the CRF model, which established the information of words, predicates, the case-frame dictionary and hypernyms of words as features, were used. This method demonstrated higher performance in comparison with the existing method, with accuracy rate of 83.13% as compared to 81.2%, respectively.

Korean Semantic Role Labeling Based on Suffix Structure Analysis and Machine Learning (접사 구조 분석과 기계 학습에 기반한 한국어 의미 역 결정)

  • Seok, Miran;Kim, Yu-Seop
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.5 no.11
    • /
    • pp.555-562
    • /
    • 2016
  • Semantic Role Labeling (SRL) is to determine the semantic relation of a predicate and its argu-ments in a sentence. But Korean semantic role labeling has faced on difficulty due to its different language structure compared to English, which makes it very hard to use appropriate approaches developed so far. That means that methods proposed so far could not show a satisfied perfor-mance, compared to English and Chinese. To complement these problems, we focus on suffix information analysis, such as josa (case suffix) and eomi (verbal ending) analysis. Korean lan-guage is one of the agglutinative languages, such as Japanese, which have well defined suffix structure in their words. The agglutinative languages could have free word order due to its de-veloped suffix structure. Also arguments with a single morpheme are then labeled with statistics. In addition, machine learning algorithms such as Support Vector Machine (SVM) and Condi-tional Random Fields (CRF) are used to model SRL problem on arguments that are not labeled at the suffix analysis phase. The proposed method is intended to reduce the range of argument instances to which machine learning approaches should be applied, resulting in uncertain and inaccurate role labeling. In experiments, we use 15,224 arguments and we are able to obtain approximately 83.24% f1-score, increased about 4.85% points compared to the state-of-the-art Korean SRL research.

Predicate Recognition Method using BiLSTM Model and Morpheme Features (BiLSTM 모델과 형태소 자질을 이용한 서술어 인식 방법)

  • Nam, Chung-Hyeon;Jang, Kyung-Sik
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.1
    • /
    • pp.24-29
    • /
    • 2022
  • Semantic role labeling task used in various natural language processing fields, such as information extraction and question answering systems, is the task of identifying the arugments for a given sentence and predicate. Predicate used as semantic role labeling input are extracted using lexical analysis results such as POS-tagging, but the problem is that predicate can't extract all linguistic patterns because predicate in korean language has various patterns, depending on the meaning of sentence. In this paper, we propose a korean predicate recognition method using neural network model with pre-trained embedding models and lexical features. The experiments compare the performance on the hyper parameters of models and with or without the use of embedding models and lexical features. As a result, we confirm that the performance of the proposed neural network model was 92.63%.

SRLev-BIH: An Evaluation Metric for Korean Generative Commonsense Reasoning (SRLev-BIH: 한국어 일반 상식 추론 및 생성 능력 평가 지표)

  • Jaehyung Seo;Yoonna Jang;Jaewook Lee;Hyeonseok Moon;Sugyeong Eo;Chanjun Park;Aram So;Heuiseok Lim
    • Annual Conference on Human and Language Technology
    • /
    • 2022.10a
    • /
    • pp.176-181
    • /
    • 2022
  • 일반 상식 추론 능력은 가장 사람다운 능력 중 하나로써, 인공지능 모델이 쉽게 모사하기 어려운 영역이다. 딥러닝 기반의 언어 모델은 여전히 일반 상식에 기반한 추론을 필요로 하는 분야에서 부족한 성능을 보인다. 특히, 한국어에서는 일반 상식 추론과 관련한 연구가 상당히 부족한 상황이다. 이러한 문제 완화를 위해 최근 생성 기반의 일반 상식 추론을 위한 한국어 데이터셋인 Korean CommonGen [1]이 발표되었다. 그러나, 해당 데이터셋의 평가 지표는 어휘 단계의 유사성과 중첩에 의존하는 한계를 지니며, 생성한 문장이 일반 상식에 부합한 문장인지 측정하기 어렵다. 따라서 본 논문은 한국어 일반 상식 추론 및 생성 능력에 대한 평가 지표를 개선하기 위해 문장 성분의 의미역과 자모의 형태 변화를 바탕으로 생성 결과를 평가하는 SRLev, 사람의 평가 결과를 학습한 BIH, 그리고 두 평가 지표의 장점을 결합한 SRLev-BIH를 제안한다.

  • PDF

Tense and Aspect in English (영어 시제와 상)

  • Kim, Jeong-O
    • The Journal of the Korea Contents Association
    • /
    • v.13 no.3
    • /
    • pp.502-510
    • /
    • 2013
  • The purpose of this paper investigate the general definition of Tense and the concepts about Aspect. I consider the correlation between the lexical and the grammatical aspect. Tense is an inflection type of a verb that indicates the time, tense is grammatical categories. Tense has the current tense and the past tense in English. If we recognize aspect as a grammatical category, that the subject of in description will be confined to the grammatical expression. In contrast, when considered as a category of meaning, lexical and grammatical representation is the expression target. Therefore, aspect is stated as a grammatical category. Specially, the aspect of English, there is only a progressive tense and perfect tense. In this case, the progressive aspect is progressive tense and the perfect aspect is perfect tense. Chapter 2, I investigate the definition of the tense of many scholars and define the usage of each tense. In Chapter 3, I exhibit the definition of the Aspect. Aspect is grammatical and semantic one. Tense and Aspect is a simple grammar category, but they have a various spectrum. Therefore, As the definition of the Tense and Aspect becomes clear it will be helpful to students who are received English education. In addition, the definition about tense and aspect needs in variety of areas, more research is needed.

Construction of Immunology Thesaurus and Ontology (면역학 시소러스 및 온톨로지 구축)

  • Im, Ji-Hui;Choe, Ho-Seop;Bae, Young-Jun;Ock, Cheol-Young;Choi, Sung-Pil;Sung, Won-Kyung;Park, Dong-In
    • Annual Conference on Human and Language Technology
    • /
    • 2005.10a
    • /
    • pp.21-27
    • /
    • 2005
  • 본 논문에서는 국가에서 추진하는 차세대신성장동력산업과 관련된 특정 분야('바이오 신약/장기' 분야 중 '면역 기능 제어')를 선택하여, 기구축된 면역학 전문용어사전을 비롯하여 의학용어사전, 표준국어대사전 등을 참조하여 핵심 용어와 관련 용어를 중심으로 면역학 시소러스(어휘 3,462개) 및 온톨로지(개념 노드 4,703개)를 구축하였다. 이것은 전문용어사전부터 온톨로지에 이르기까지 통일화된 표준 체계를 가지고 있으며, 도메인 온톨로지를 구축하여 향후 온톨로지 개발 방향을 설정할 수 있는 계기가 되었다고 할 수 있다. 또한 면역학 시소러스는 검색의 성능을 향상시킬 수 있도록 충분한 양의 데이터를 구축하였고 면역학 온톨로지는 언어처리적 관점에서의 온톨로지를 표현하였다. 이는 정보검색에서의 효율성을 비롯하여, 특정 웹 온톨로지 언어를 이용한 웹 온톨로지로의 변환성, 대규모 도메인 온톨로지라는 점에서 의미를 가진다고 할 수 있다.

  • PDF

Interpretation and Preservation Plan for Landscapes of Okyeonsipyeong at Buyongdae, Hahoe Village - Based on the Writings of "Okyeonseodanggi" and "Okyeonsipyeong" - (하회마을 부용대의 경관 해석 및 보전방안 - "옥연서당기(玉淵書堂記)"와 "옥연십영(玉淵十詠)"을 중심으로-)

  • Rho, Jae-Hyun;Oh, Hyun-Kyung;Shin, Sang-Sup
    • Journal of the Korean Institute of Traditional Landscape Architecture
    • /
    • v.31 no.1
    • /
    • pp.59-70
    • /
    • 2013
  • This study was to suggest cultural landscape preservation, value creation, as well as utilization plan to help landscape development of Hahoe village by identify the existence of Okyeonsipyeong(玉淵十詠) natural features, which were set around Buyongdae(芙蓉臺) in Hahoe Village by Seoae(西崖) Ryu, Seongryong(柳成龍), and understanding their characteristics and meanings of natural features and meanings. Based on the writings of "Okyeonseodanggi" and "Okyeonsipyeong", the major results of this study are as belows. 'Okyeon(玉淵)' letters carved on the rocks, also known as the name of pavilion in Okyeonjeongsa(玉淵精舍), is the center of Okyeonsipyeong that symbolizes the enlightenment of clean noble man, as well as the symbolic locational expression of studying room. One of Okyeonsipyeong, 'Wansimjae', is assumed to be the name from the combination of two Buddhist names, 'Wanjeok(玩寂)' and 'Seshim(洗心)', 'Dangho(堂號)', lined on both sides with Wonlakjae, the residence of Seoae, as the center. Wansimjae is after all the natural feature indicating the overall Okyeonjeongsa as the core of Okyeonsipyeong with west edge Gyeomamjeongsa(謙巖精舍). Among ten Okyeonsipyeong natural features, Wansimjae(玩心齋), Ganjukmun(看竹門), Gyeomamsa(謙菴舍), Dalgwandae(達觀臺), Ssangsongae(雙松厓), and Dohwacheon (桃花遷) are on the right side of the stairway from Okyeonjeongsa to Gyeomamjeongsa, while Chuwoldam(秋月潭), Neungpadae(凌波臺), Gyeseonam(繫船巖), and Jijuam(砥柱巖) are on the road to the cliff under river cliff in Buyongdae as well as to the dock, and all are located within 500m radius close and diameter area. As the results of lexeme and context analyses of Okyeonsipyeong poet, they are mainly about Confucian teachings symbolizing the constancy of the classical scholar including ego becoming one with the nature and back to the nature, unworldliness and farsighted view, transcendence and seclusion, as well as integrity spirit. In Dohwacheon and Gyeomamsa poets, there is Tao characteristics and brotherhood that pursue fairylands such as Mooreungdowon(武陵桃源). To create tourism brand and landscape of Okyeonsipyeong, it is necessary to prepare storytelling plans including the letters carved on the rocks introduction in Buyongdae area, and also synopsis of the Silgyeongsusang musical, 'Buyongjiae(芙蓉之愛)' that is related to 10 natural features. In addition, the related plans of the experience road from Gyeseonam, which is the boat stop in Buyongdae, to Ganjukmun of Okyeonjeongsa, and again to viewing routes on the stairways to Gyeomamjeongsa using boats are necessary. For preliminary preservation and maintenance plans, the safety of the stairway from Okyeonjeongsa to Gyeomamjeongsa should be secured, the rock inscription should be preserved, landscape interpretation plates should be installed, trees and shrubs around Dohwacheon rock inscription should be removed, Dalgwandae letters carved on the rocks should be restored, and the bamboo forest outside Ganjukmun as well as Prunus persica plantation around Dohwacheon should be pointed out.