• 말소리와 음성과학
• /
• 제13권2호
• /
• pp.37-44
• /
• 2021

Preliminary findings are reported from five experiments testing the perceived naturalness of word tokens whose vowel durations are altered. The stimuli were minimal pairs of English words ending in a voiced/voiceless plosive. Results show an asymmetric effect of shortening and lengthening of the vowel on the perceived naturalness of the word. Incremental shortening of vowel duration initially shows a stable degree of perceived naturalness but rapidly deteriorates beyond a certain point. On the contrary, only a small degree of lengthening of the vowel made the perceived naturalness of the word quickly decay, but there was a floor effect such that the perceived degree of naturalness does not lower beyond a certain level. Further, the tokens with the original vowel duration were not always scored higher than the stimuli with a small degree of shortening. Future studies should address the issue of speaking rate and the ratio between the vowel and the stop closure duration to better understand the phenomenon. The issue investigated here has implications on the role of prototypical exemplars in the perception of phonotactic naturalness.

• 한국ITS학회 논문지
• /
• 제15권4호
• /
• pp.26-32
• /
• 2016

자율주행자동차는 운전자의 조작 없이 목표지점까지 스스로 주행환경을 인식하여 운행하는 최첨단 자동차를 말하며 위성항법장치, 센서 등으로 위치를 측정하고 주행환경을 인식, 연산장치로 가감속 차선변경 등 자율주행을 제어한다. 최근, 자동차 산업은 기존 기계공학과 정보통신, 센서, 위성항법 등 첨단기술이 총 집약된 자율주행 자동차로 빠르게 진화중이다. 교통안전 정책과제 분석은 Issue-Tree를 활용하여 분석하였다. Issue-Tree 방법론은 복잡한 문제를 세분화하여 구체화하고, 체계적으로 접근하는 문제해결 도구로 자율주행자동차 도입에 따른 교통안전 관련 Issue의 해결을 위한 정책과제를 도출하기 위해 사용된다. 교통안전 정책과제를 분석하기 위해는 우선 미래 사회 및 교통여건 변화로부터 Key Word를 도출하고, 이와 연계되는 국내외 도로교통 정책/계획을 확인하여 국내외 도로 교통 정책목표 Key Word를 도출하였다. 도출된 정책목표 Key Word로부터 핵심적인 Issue를 도출하였는데, 이때 Issue-Tree 방법을 통해 체계화하였다.

• 음성과학
• /
• 제11권3호
• /
• pp.37-54
• /
• 2004

The main goal of this study is to examine the current issue of the deletion of high tone vs. the downstep or upstep of high tone in North Kyungsang Korean (NKK). In this phonetic experiment, five native speakers of North Kyungsang Korean participated and two categories, such as compounds and two-word phrases were included as a test material. This experiment shows that when the first word belongs to the nonfinal class, the high tone of the second word is overwhelmingly deleted. When the first word belongs to the final class, the high tone of it is also overwhelmingly deleted. It is thus concluded that when two words are combined into a phrase, the peak of one word retains, whereas the peak of the other is deleted. It is confirmed that a single high tone prominence in a phonological phrase in NKK is not due to the processes of down step or upstep but the deletion process.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권1호
• /
• pp.254-276
• /
• 2019

Since the amount of information on the internet is growing rapidly, it is not easy for a user to find relevant information for his/her query. To tackle this issue, the researchers are paying much attention to Document Summarization. The key point in any successful document summarizer is a good document representation. The traditional approaches based on word overlapping mostly fail to produce that kind of representation. Word embedding has shown good performance allowing words to match on a semantic level. Naively concatenating word embeddings makes common words dominant which in turn diminish the representation quality. In this paper, we employ word embeddings to improve the weighting schemes for calculating the Latent Semantic Analysis input matrix. Two embedding-based weighting schemes are proposed and then combined to calculate the values of this matrix. They are modified versions of the augment weight and the entropy frequency that combine the strength of traditional weighting schemes and word embedding. The proposed approach is evaluated on three English datasets, DUC 2002, DUC 2004 and Multilingual 2015 Single-document Summarization. Experimental results on the three datasets show that the proposed model achieved competitive performance compared to the state-of-the-art leading to a conclusion that it provides a better document representation and a better document summary as a result.

• Journal of Information Technology Applications and Management
• /
• 제23권2호
• /
• pp.11-28
• /
• 2016

In this paper, we proposed a dictionary extension and a ternary decomposition technique to improve the effectiveness of Khmer word segmentation. Most word segmentation approaches depend on a dictionary. However, the dictionary being used is not fully reliable and cannot cover all the words of the Khmer language. This causes an issue of unknown words or out-of-vocabulary words. Our approach is to extend the original dictionary to be more reliable with new words. In addition, we use ternary decomposition for the segmentation process. In this research, we also introduced the invisible space of the Khmer Unicode (char\u200B) in order to segment our training corpus. With our segmentation algorithm, based on ternary decomposition and invisible space, we can extract new words from our training text and then input the new words into the dictionary. We used an extended wordlist and a segmentation algorithm regardless of the invisible space to test an unannotated text. Our results remarkably outperformed other approaches. We have achieved 88.8%, 91.8% and 90.6% rates of precision, recall and F-measurement.

• Management Science and Financial Engineering
• /
• 제11권3호
• /
• pp.47-60
• /
• 2005

Well-known e-CRM strategy is to focus on profitable customers and pay less attention to unprofitable ones. Moreover, some researchers recommend not serving unprofitable ones any more. However, it often neglects customers indirect value. Deselecting unprofitable customers can raise the issue of bad word-of-mouth publicity especially in the age of the Internet. Some studies pointed out that a customers decision to buy a product or service is often strongly influenced by others. In this paper, we consider customers' word-of-mouth effect on quality learning of inexperienced customers. We show that firms implementing e-CRM must take the effect into the consideration when deselecting unprofitable customers.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2020년도 제62차 하계학술대회논문집 28권2호
• /
• pp.307-310
• /
• 2020

본 논문에서 이슈 키워드 추출을 위해 텍스트 마이닝(Text Mining) 기술을 요구한다. 사회적 이슈 키워드를 추출하기 위해 키워드 수집 모델이 되는 사이트에서 크롤링(crawling)을 수행한 뒤, 형태소 단위 의미있는 단어를 수집하기 위해 형태소 분석(morphological analysis)을 수행한다. 한국어 형태소 분석을 위해 파이썬의 코엔엘파이(KoNLPy) 패키지를 활용한다. 형태소 분석을 통해 나뉘어진 단어에서 통계를 내어 이슈 키워드 추출한다. 이슈 키워드를 뒷받침할 연관 단어를 분석하기 위해 단어 임베딩(Word Embedding)을 수행한다. 단어 임베딩 수행을 위해 Word2Vec 모델 중 Skip-Gram 방법론을 적용하여 연관 단어를 분석하도록 개발하였다. 웹 소켓(Web Socket) 통신을 통한 채팅 프로그램의 상단에 분석한 이슈 키워드와 연관 단어를 출력하도록 개발하였다.

• 한국콘텐츠학회논문지
• /
• 제16권3호
• /
• pp.269-287
• /
• 2016

이 연구는 유병언 사망 사건과 관련된 언론 보도를 네트워크 분석하고, 이 사건이 소셜네트워크사이트를 통해 어떻게 확산되는지 이슈의 확산 과정을 네트워크 분석했다. 지상파 언론과 종편을 분석 대상으로 언론보도의 이슈 현저성, 단어의 가시성과 연결성을 분석했다. 네트워크 분석 결과 종편은 사건과 관련된 핵심 정보보다는 유병언 유류품, 브랜드, 시신에 대한 루머를 강조했고, 지상파 방송은 국과수의 DNA 검사 결과를 중심으로 보도했다. 시기별로 보면 1기 지상파는 '유병언 시신 발견 프레임'을, 종편은 '수사 비난 프레임', '명품 강조 프레임'으로 사건을 틀지었다. 2기 지상파는 '유병언 사인 분석 프레임'을, 종편은 '의혹 제기 프레임'을 강조했다. 3기 지상파는 몇 건 밖에 보도하지 않아 분석의 의미가 없고 종편은 '주변 정보 강조 프레임'이 부각되었다. 언론의 보도는 유투브와 SNS를 통해 확산되었는데, 네트워크 분석 결과 유병언 사망과 관련된 루머가 주목을 받은 것으로 나타났다. 인터넷과 SNS의 발달로 독자들이 적극적으로 의견을 표출하면서 루머를 확산시킨 것으로 생각된다. 음모론의 확산 과정에서 주류 언론은 종편의 선정적이고 자극적인 보도에 밀려 영향을 발휘하지 못했음이 밝혀졌다.

• 음성과학
• /
• 제14권1호
• /
• pp.7-19
• /
• 2007

The present study investigates the so-called frequency inheritance effect in word production. According to some earlier studies (e.g. Jescheniak & Levelt, 1994), retrieval of a low-frequency homophone benefits from its high-frequency homophone twin, and more specifically word-retrieval RT is determined by the frequency of the phonological form of the word (sum of homophone frequencies) rather than the frequency of the specific word. This result, however, has been challenged by later studies (e.g. Caramazza et al., 2001) and one possible resolution is that languages differ in the extent to which the inheritance effect occurs. Two experiments are reported to test whether the frequency inheritance effect depends on the target language, namely, if a language such as Korean with relatively many homophones tend not to show frequency inheritance, which is compared with the language with fewer homophones such as Dutch and German (Jescheniak & Levelt, 1994; Jescheniak et al., 2003). Experiment 1 was picture naming, and Experiment 2 used an English-to-Korean translation task. In both experiments, the homophones were actually slower than the low-frequency controls, suggesting that there was no evidence for the inheritance effect. These results imply that the issue of whether specific word or homophone frequency determines production can be properly assessed by taking into account the language-specific nature of the lexicon such as the percentage of the homophone words in that language.

• Asia Marketing Journal
• /
• 제22권3호
• /
• pp.1-28
• /
• 2020

With the development of information and communication technology and spread of smart devices, online information exchange has become a daily routine. Accordingly, the management and utilization of online word of mouth (WOM) has become an important issue for companies. Numerous studies have examined the impact of online WOM on firm performance. This study analyzes the impact of negative word of mouth (NWOM) on firm value, considering the influence of corporate social responsibility (CSR) activity and research and development (R&D) investment. Using a hierarchical linear model, we find that 1) NWOM has a negative impact on firm value, 2) CSR activities do not significantly influence this impact, and 3) R&D investment reduces this negative impact. This study contributes by demonstrating the effect of NWOM on firm value, examining the influence of CSR activities and R&D investment on the impact of NWOM, and confirming that the hierarchical linear model can be applied effectively to panel data in empirical studies. As a practical implication, companies must prevent and manage NWOM, whose impact, when caused by an unavoidable incident, can be alleviated by proactively announcing that the company is striving for competitiveness, for instance, by investing in R&D.