• The Korean Journal of Food & Health Convergence
• /
• v.7 no.3
• /
• pp.1-11
• /
• 2021

Purpose of the research: This study aims to explain the state of marketing using fun among recent popular marketing strategies. Although companies are using various differentiated marketing strategies to gain a competitive edge, among them, fun marketing has constituted the most effective area of interest recently. Research design and methodology: To extract the customer selection attributes of fun marketing, after reviewing the literature, six optional attributes were selected from the factors of fun marketing towards consumers such as funny design, language play, celebrity use, funny taste, how to eat, and newtro (new + retro). Out of 300 questionnaires, 276 were used for analysis, excluding unscrupulous or incomplete questionnaires. The results were reviewed for validity and reliability using SPSS andAMOS, and the hypothesis was verified using structural equation modelling (SEM). Principal results: The results showed that funny design, language play, and newtro statistically significantly affected customer satisfaction, but celebrity use, funny taste, and eating methods had no significant effect. It was also confirmed that satisfaction had a statistically significant effect on repurchase intention. Major conclusions: This study can serve as basic data to enhance the marketing strategy of the food service industry, and it provides theoretical and practical implications.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.45-55
• /
• 2022

Recently, large-scale language models (LPLM) have been shown state-of-the-art performances in various tasks of natural language processing including intent classification. However, fine-tuning LPLM requires much computational cost for training and inference which is not appropriate for dialog system. In this paper, we propose compressed intent classification model for multi-agent in low-resource like CPU. Our method consists of two stages. First, we trained sentence encoder from LPLM then compressed it through knowledge distillation. Second, we trained agent-specific adapter for intent classification. The results of three intent classification datasets show that our method achieved 98% of the accuracy of LPLM with only 21% size of it.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4184-4202
• /
• 2021

Text steganography combined with natural language generation has become increasingly popular. The existing methods usually embed secret information in the generated word by controlling the sampling in the process of text generation. A candidate pool will be constructed by greedy strategy, and only the words with high probability will be encoded, which damages the statistical law of the texts and seriously affects the security of steganography. In order to reduce the influence of the candidate pool on the statistical imperceptibility of steganography, we propose a steganography method based on a new sampling strategy. Instead of just consisting of words with high probability, we select words with relatively small difference from the actual sample of the language model to build a candidate pool, thus keeping consistency with the probability distribution of the language model. What's more, we encode the candidate words according to their probability similarity with the target word, which can further maintain the probability distribution. Experimental results show that the proposed method can outperform the state-of-the-art steganographic methods in terms of security performance.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.73-80
• /
• 2021

Nowadays microblogs have become the most popular platforms to obtain and spread information. Twitter is one of the most used platforms to share everyday life event. However, rumors and misinformation on Arabic social media platforms has become pervasive which can create inestimable harm to society. Therefore, it is imperative to tackle and study this issue to distinguish the verified information from the unverified ones. There is an increasing interest in rumor detection on microblogs recently, however, it is mostly applied on English language while the work on Arabic language is still ongoing research topic and need more efforts. In this paper, we propose a combined Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) to detect rumors on Twitter dataset. Various experiments were conducted to choose the best hyper-parameters tuning to achieve the best results. Moreover, different neural network models are used to evaluate performance and compare results. Experiments show that the CNN-LSTM model achieved the best accuracy 0.95 and an F1-score of 0.94 which outperform the state-of-the-art methods.

• International Journal of Computer Science & Network Security
• /
• v.23 no.6
• /
• pp.162-168
• /
• 2023

This article presents an examination of the major cognitive-semantic theories in linguistics (Langacker, Lakoff, Fillmore, Croft). The CST's foundations are discussed concerning the educational policy changes, which are necessary to improve the linguistic disciplines in the changing context of higher education, as well as the empowerment and development of the industry. It is relevant in the light of the linguistic specialists' quality training and the development of effective methods of language learning. Consideration of the theories content, tools, and methods of language teaching, which are an important component of quality teaching and the formation of a set of knowledge and skills of students of linguistic specialties, remains crucial. This study aims to establish the main theoretical positions and directions of cognitive-semantic theory in linguistics, determine the usefulness of teaching the basics of cognitive linguistics, the feasibility of using methods of cognitive-semantic nature in the learning process. During the research, the methods of linguistic description and observation, analysis, and synthesis were applied. The result of the study is to establish the need to study basic linguistic theories, as well as general theoretical precepts of cognitive linguistics, which remains one of the effective directions in the postmodern mainstream. It also clarifies the place of the main cognitive-semantic theories in the teaching linguistics' practice of the XXI century.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.744-751
• /
• 2022

Construction is among the most dangerous industries with numerous accidents occurring at job sites. Following an accident, an investigation report is issued, containing all of the specifics. Analyzing the text information in construction accident reports can help enhance our understanding of historical data and be utilized for accident prevention. However, the conventional method requires a significant amount of time and effort to read and identify crucial information. The previous studies primarily focused on analyzing related objects and causes of accidents rather than the construction activities. This study aims to extract construction activities taken by workers associated with accidents by presenting an automated framework that adopts a deep learning-based approach and natural language processing (NLP) techniques to automatically classify sentences obtained from previous construction accident reports into predefined categories, namely TRADE (i.e., a construction activity before an accident), EVENT (i.e., an accident), and CONSEQUENCE (i.e., the outcome of an accident). The classification model was developed using Convolutional Neural Network (CNN) showed a robust accuracy of 88.7%, indicating that the proposed model is capable of investigating the occurrence of accidents with minimal manual involvement and sophisticated engineering. Also, this study is expected to support safety assessments and build risk management systems.

• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.430-435
• /
• 1997

통계적인 방법으로 병렬 코퍼스(parallel corpus)로부터 사전정보를 추출해 내는 정렬 시스템에 대한 연구가 세계 여러곳에서 진행되고 있다(신중호 1996; Dagan 1996; Fung 1995; Kupiec 1993). 그 결과로 만들어진 사전정보는 유용한 대역어와 대역 확률을 포함하고 있지만, 불필요하거나 잘못된 요소들도 많이 포함되어 있어 재조정 작업이 필요하다. 이는 사전정보를 직관적으로 확인함으로써 조정을 할 수도 있지만, 좀 더 정확한 조정을 위해 각각의 사전정보(정렬의 결과)가 코퍼스의 어떤 문장에서 나온 것인가 등을 확인할 필요가 있다. 정렬 워크벤치는 이와 같은 작업을 효율적으로 처리할 수 있도록 만들어졌으며, 현재 구현되어 작동되고 있다. 본 논문에서는 정렬 워크벤치를 위해 필요한 정렬시스템의 변형과 사전작업의 편의를 위해 제공되어져야 하는 기능 등에 관하여 설명하고, 간단한 평가 결과를 설명한다.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2002.02a
• /
• pp.59-68
• /
• 2002

In this paper, we address two questions concerning negative imperatives in Korean: (i) what is the morpho-syntactic nature of mal in negative imperatives\ulcorner; and (ii) why is it impossible to form negative imperatives with short negation an\ulcorner We will argue that the clause structure of imperatives include a projection of deontic modality and a projection of imperative operator encoding illocutionary force, and that oaf is a lexicalization of long negation and deontic modality. We then propose that a negative imperative with short negation is ruled out because such construction maps onto incoherent interpretation which can be spelled out as I direct you to bring about a negative state or a negative event.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.9-13
• /
• 2016

Stack LSTM기반 의존 파싱은 전이 기반 파싱에서 스택과 버퍼의 내용을 Stack LSTM으로 인코딩하여 이들을 조합하여 파서 상태 벡터(parser state representation)를 유도해 낸후 다음 전이 액션을 결정하는 방식이다. Stack LSTM기반 의존 파싱에서는 버퍼 초기화를 위해 단어 표상 (word representation) 방식이 중요한데, 한국어와 같이 형태적으로 복잡한 언어 (morphologically rich language)의 경우에는 무수히 많은 단어가 파생될 수 있어 이들 언어에 대해 단어 임베딩 벡터를 직접적으로 얻는 방식에는 한계가 있다. 본 논문에서는 Stack LSTM 을 한국어 의존 파싱에 적용하기 위해 음절-태그과 형태소의 표상들을 결합 (hybrid)하여 단어 표상을 얻어내는 합성 방법을 제안한다. Sejong 테스트셋에서 실험 결과, 제안 단어표상 방법은 음절-태그 및 형태소를 이용한 방법을 더욱 개선시켜 UAS 93.65% (Rigid평가셋에서는 90.44%)의 우수한 성능을 보여주었다.

• Annual Conference on Human and Language Technology
• /
• 1998.10c
• /
• pp.97-104
• /
• 1998

인터넷의 사용자가 폭발적으로 증가함에 따라, 인터넷을 이용한 다양한 정보 서비스가 생성되었으며, 이로 인해 일반 사용자들이 접할 수 있는 디지털 문서의 양은 기하 급수적으로 증가 되었다. 본 논문에서는 유사한 정보를 갖는 다량의 문서들로부터 사용자가 원하는 정보만을 추출하는 정보 추출 시스템의 개발 과정 및 결과를 기술한다. 개발된 시스템은 필요한 정보를 포함하는 문장들을 걸러 낸 후, 필요한 사실정보의 출현을 나타내는 패턴을 사용한 유한 오토마타를 통하여 사용자가 원하는 정보를 추출한다. 관광지 안내 텍스트를 대상으로 한 실험 및 분석 결과를 기술한다.