• ETRI Journal
• /
• 제35권5호
• /
• pp.838-848
• /
• 2013

This paper presents a novel approach to automatically generate Korean multiword sentiment expressions by using a seed sentiment lexicon and a large-scale domain-specific corpus. A multiword sentiment expression consists of a seed sentiment word and its contextual words occurring adjacent to the seed word. The multiword sentiment expressions that are the focus of our study have a different polarity from that of the seed sentiment word. The automatically extracted multiword sentiment expressions show that 1) the contextual words should be defined as a part of a multiword sentiment expression in addition to their corresponding seed sentiment word, 2) the identified multiword sentiment expressions contain various indicators for polarity shift that have rarely been recognized before, and 3) the newly recognized shifters contribute to assigning a more accurate polarity value. The empirical result shows that the proposed approach achieves improved performance of the sentiment analysis system that uses an automatically generated lexicon.

• 지능정보연구
• /
• 제22권1호
• /
• pp.83-105
• /
• 2016

의료IT 서비스의 유망 분야인 정신건강 증진을 위한 주관적 웰빙 서비스(subjective well-being service) 구현의 핵심은 개인의 주관적 웰빙 상태를 정확하고 무구속적이며 비용 효율적으로 측정하는 것인데 이를 위해 보편적으로 사용되는 설문지에 의한 자기보고나 신체부착형 센서 기반의 측정 방법론은 정확성은 뛰어나나 비용효율성과 무구속성에 취약하다. 비용효율성과 무구속성을 보강하기 위한 온라인 텍스트 기반의 측정 방법은 사전에 준비된 감정어 어휘만을 사용함으로써 상황에 따라 감정어로 볼 수 있는 이른바 상황적 긍부정성(contextual polarity)을 고려하지 못하여 측정 정확도가 낮다. 한편 기존의 상황적 긍부정성을 활용한 감성분석으로는 주관적 웰빙 상태인 맥락에서의 감성분석을 할 수 있는 감정어휘사전이나 온톨로지가 구축되어 있지 않다. 더구나 온톨로지 구축도 매우 노력이 소요되는 작업이다. 따라서 본 연구의 목적은 온라인상에 사용자의 의견이 표출된 비정형 텍스트로부터 주관적 웰빙과 관련한 상황감정어를 추출하고, 이를 근거로 상황적 긍부정성 파악의 정확도를 개선하는 방법을 제안하는 것이다. 기본 절차는 다음과 같다. 먼저 일반 감정어휘사전을 준비한다. 본 연구에서는 가장 대표적인 디지털 감정어휘사전인 SentiWordNet을 사용하였다. 둘째, 정신건강지수를 동적으로 추정하는데 필요한 비정형 자료인 Corpora를 온라인 서베이로 확보하였다. 셋째, Corpora로부터 세 가지 종류의 자원을 확보하였다. 넷째, 자원을 입력변수로 하고 특정 정신건강 상태의 지수값을 종속변수로 하는 추론 모형을 구축하고 추론 규칙을 추출하였다. 마지막으로, 추론 규칙으로 정신건강 상태를 추론하였다. 본 연구는 감정을 분석함에 있어, 기존의 연구들과 달리 상황적 감정어를 적용하여 특정 도메인에 따라 다양한 감정 어휘를 파악할 수 있다는 점에서 독창성이 있다.

• Architectural research
• /
• 제15권4호
• /
• pp.191-200
• /
• 2013

Since Modern Movement flexibility has been one of the most attractive words in architecture. However, "overprovision first, division later" has been the most prevailing design method for spatial flexibility, and many of buildings designed for flexible use are practically quite inflexible due to insufficient building systems or/and irresponsible planning. There have been two dominant strategies to achieve architectural flexibility: multi-functionality and polyvalence. These two approaches, which point contradictory directions, actually reflect the difficulty in providing a proper form of architectural flexibility. Multi-functionality can afford changeable environments with satisfying spatial conditions; however it lacks tolerance to accommodate other uses but intended functions by architects. Meanwhile, flexibility by a polyvalent form relies on the vague anticipation of user's various interpretations. In this study by looking up these two different standpoints and historical precedents flexibility in architecture is carefully scrutinized focused on the contradiction, and as an alternative for architectural flexibility contextual relations is proposed. Unlike both multi-functionality and polyvalence, which produce flexibility by changing its own properties, manipulating contextual relations infuses flexibility into space by changing the properties of a building, not of its individual room. By using this contextual relations method, a community-centered school in Manhattan, NY, which was in danger of being closed because of its academic failure, is represented as a flexible space.

• 정보처리학회논문지B
• /
• 제15B권1호
• /
• pp.73-80
• /
• 2008

본 연구에서는 문서 클러스터링을 이용하여 동음 이의어와 핵심단어 선정 실패로 인해 발생하는 자동 광고 시스템의 오류를 해결하는 광고 키워드 추출방식을 제안한다. 먼저 대규모 뉴스기사를 대상으로 유사한 내용을 가지며 동일한 광고 키워드와 연관이 있는 기사들을 자동으로 분류하여 광고 키워드에 대한 문맥 정보를 구축한다. 또한 광고 대상물에 대한 광고주의 요약 정보나 광고 대상 웹페이지를 분석하여 광고 키워드에 대한 문맥 정보를 추출하는 방식을 보인다. 이렇게 구축된 문서 분류와 광고 키워드용 문맥 정보를 이용하여 광고 대상 문서가 속한 문서 분류를 추정하여 단어들의 의미적인 애매성을 해결하고, 추정한 문서 분류와 관련 있으면서 문맥적으로 중요성을 가지는 핵심 단어들을 선정하여 광고 키워드를 추출한다. 상용 광고 시스템과의 비교 분석 결과 신문 기사나 일반 블로그를 대상으로 최소 21%의 성능 향상을 얻었다.

• 한국컴퓨터정보학회논문지
• /
• 제20권10호
• /
• pp.69-76
• /
• 2015

User's selection of music is largely influenced by private tastes as well as emotional states, and it is the unconsciousness projection of user's emotion. Therefore, we think user's emotional states to be music itself. In this paper, we try to grasp user's emotional states from music selected by users at a specific context, and we analyze the correlation between its context and user's emotional state. To get emotional states out of music, the proposed method extracts emotional words as the representative of music from lyrics of user-selected music through morphological analysis, and learns weights of linear classifier for each emotional features of extracted words. Regularities learned by classifier are utilized to calculate predictive weights of virtual music using weights of music chosen by other users in context similar to active user's context. Finally, we propose a method to recommend some pieces of music relative to user's contexts and emotional states. Experimental results shows that the proposed method is more accurate than the traditional collaborative filtering method.

• 말소리와 음성과학
• /
• 제3권4호
• /
• pp.71-81
• /
• 2011

This paper investigated how prosodic position and word type affect the phonetic structure of Korean coronal stops. Initial segments of prosodic domains were known to be more strongly articulated and longer relative to prosodic domain-medial segments. However, there are few studies examining whether the properties of prosodic domain-initial segments are affected by the information content of words (real vs. nonsense words). In addition, since the scope of domain-initial effect was known to be local to the initial consonant and the effects on the following vowel have been found to be limited, it is thus worth examining whether the prosodic domain-initial effect extends into the vowel after the initial consonant in a systematic way across different prosodic domains. The acoustic properties of Korean coronal stops (lenis /t/, aspirated /$t^h$/, and tense /t'/) were compared across Intonational Phrase, Phonological Phrase and Word-initial positions both in real and nonsense words. The durational intervals such as VOT and CV duration were cumulatively lengthened for /t/ and /$t^h$/ in the higher prosodic domain-initial positions. However, tense stop /t'/ did not show any variation as a function of prosodic position and word type. The domain-initial lenis stop showed significantly longer duration in nonsense words than in real words. But the prosodic domain-initial effect was not found in the properties of F0 and [H1-H2] of the vowel after initial stops. The present study provided evidence that speakers tend to enhance speech clarity when there is less contextual information as in prosodic domain-initial position and in nonsense words.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3168-3186
• /
• 2020

Automatic topic essay generation (TEG) is a controllable text generation task that aims to generate informative, diverse, and topic-consistent essays based on multiple topics. To make the generated essays of high quality, a reasonable method should consider both diversity and topic-consistency. Another essential issue is the intrinsic link of the topics, which contributes to making the essays closely surround the semantics of provided topics. However, it remains challenging for TEG to fill the semantic gap between source topic words and target output, and a more powerful model is needed to capture the semantics of given topics. To this end, we propose a pretraining-based contextual self-attention (PC-SAN) model that is built upon the seq2seq framework. For the encoder of our model, we employ a dynamic weight sum of layers from BERT to fully utilize the semantics of topics, which is of great help to fill the gap and improve the quality of the generated essays. In the decoding phase, we also transform the target-side contextual history information into the query layers to alleviate the lack of context in typical self-attention networks (SANs). Experimental results on large-scale paragraph-level Chinese corpora verify that our model is capable of generating diverse, topic-consistent text and essentially makes improvements as compare to strong baselines. Furthermore, extensive analysis validates the effectiveness of contextual embeddings from BERT and contextual history information in SANs.

• Journal of Multimedia Information System
• /
• 제9권2호
• /
• pp.93-102
• /
• 2022

Dependency parsing is a decision problem of the syntactic relation between words in a sentence. Recently, deep learning models are used for dependency parsing based on the word representations in a continuous vector space. However, it causes a mislabeled tagging problem for the proper nouns that rarely appear in the training corpus because it is difficult to express out-of-vocabulary (OOV) words in a continuous vector space. To solve the OOV problem in dependency parsing, we explored the proper noun embedding method according to the embedding unit. Before representing words in a continuous vector space, we replace the proper nouns with a special token and train them for the contextual features by using the multi-layer bidirectional LSTM. Two models of the syllable-based and morpheme-based unit are proposed for proper noun embedding and the performance of the dependency parsing is more improved in the ensemble model than each syllable and morpheme embedding model. The experimental results showed that our ensemble model improved 1.69%p in UAS and 2.17%p in LAS than the same arc-eager approach-based Malt parser.

• 한국수학교육학회지시리즈C:초등수학교육
• /
• 제25권4호
• /
• pp.361-375
• /
• 2022

이 연구에서는 2015 개정 교육과정에 따른 초등학교 1~2학년 수학 교과서 어휘를 등급 및 유형에 따라 분석하였다. 어휘 유형은 학습 도구어, 수학 교과 특수 개념어, 수학 교과 일반 개념어로 구분하여 분석하였다. 어휘 등급별 분석 결과, 1~2학년 수학 교과서에서는 1등급과 2등급 어휘가 대부분을 차지하고 있었다. 어휘 유형별 분석 결과, 학습 도구어 중 일부 어휘가 3등급 어휘로 나타났으며, 수학 교과 특수 개념어의 경우 미등록어이거나 1등급 어휘인 경우들이 많았다. 수학 교과 일반 개념어는 2학년 교과서에서의 빈도수가 1학년 교과서에 비해 크게 증가하였다. 이러한 결과를 기반으로 수학 교과서 어휘 지도를 위한 시사점을 제시하였다.

• International Journal of Contents
• /
• 제7권1호
• /
• pp.37-44
• /
• 2011

This research attempts to analyze brand placement in game. Brand placement, being acclaimed as a new beneficiary model in game industry, is raising important mean of advertising. For development of game industry, the interdisciplinary study between game and advertising is indispensible. Therefore, the purpose of this study is to find creative types of brand placement in game for illuminating how advertising works in game contents. The results showed three types of brand placement in game. They are contextual type, prominent type and independent type. Contextual type is one where the brand is present within the game contents without being formally expressed: it plays a passive role. Prominent type is one where the brand is present within the game contents with being formally expressed: it plays an active role. Independent type is one where the brand is present within the game contents with being formally expressed but it is not related with the program: it plays an additional role. The research showed, among these three types, a prominent type is becoming mainstream of brand placement in game. In other words, the prominent type of brand placement is the most effective beneficial alternative in game industry.