• The Journal of Asian Finance, Economics and Business
• /
• 제9권5호
• /
• pp.273-283
• /
• 2022

Banking and finance is a broad term that incorporates a variety of smaller, more specialized subjects such as corporate finance, tax finance, and insurance finance. A virtual assistant that assists users in searching for information about banking and finance terms might be an extremely beneficial tool for users. In this study, we explored the process of searching for information, seeking opportunities, and developing a virtual assistant in the first stages of starting learning and understanding Vietnamese to increase effectiveness and save time, which is also an innovative business practice in Use-case Vietnam. We built the FIBA2020 dataset and proposed a pipeline that used Natural Language Processing (NLP) inclusive of Natural Language Understanding (NLU) algorithms to build chatbot applications. The open-source framework RASA is used to implement the system in our study. We aim to improve our model performance by replacing parts of RASA's default tokenizers with Vietnamese tokenizers and experimenting with various language models. The best accuracy we achieved is 86.48% and 70.04% in the ideal condition and worst condition, respectively. Finally, we put our findings into practice by creating an Android virtual assistant application using the model trained using Whitespace tokenizer and the pre-trained language m-BERT.

• 센서학회지
• /
• 제30권6호
• /
• pp.429-435
• /
• 2021

In this study, the creation of emotional dialogue was investigated within the process of developing a robot's natural language understanding and emotional dialogue processing. Unlike an English-based dataset, which is the mainstay of natural language processing, the Korean-based dataset has several shortcomings. Therefore, in a situation where the Korean language base is insufficient, the Korean dataset should be dealt with in detail, and in particular, the unique characteristics of the language should be considered. Hence, the first step is to base this study on a specific Korean dataset consisting of conversations on emotional topics. Subsequently, a model was built that learns to extract the continuous dialogue features from a pre-trained language model to generate sentences while maintaining the context of the dialogue. To validate the model, a chatbot system was implemented and meaningful results were obtained by collecting the external subjects and conducting experiments. As a result, the proposed model was influenced by the dataset in which the conversation topic was consultation, to facilitate free and emotional communication with users as if they were consulting with a chatbot. The results were analyzed to identify and explain the advantages and disadvantages of the current model. Finally, as a necessary element to reach the aforementioned ultimate research goal, a discussion is presented on the areas for future studies.

• 디자인학연구
• /
• 제20권1호
• /
• pp.55-64
• /
• 2007

비언어적 의사소통 수단은 언어적 의사소통을 보조하고 대체한다는 점에서 매우 중요하다. 다양한 비언어적 의사소통 수단 중 신체언어는 몸을 통한 의사소통 전반을 말한다. 애니메이션의 경우, 시나리오 전달에 있어서 캐릭터가 가장 중요한 역할을 하므로 이와 같은 신체언어 연출은 매우 중요한 요소 중 하나이다. 애니메이션의 의사소통 구조는 일반적인 의사소통 구조와는 달리 이중적인 의사소통 구조를 가지는데, 첫째는 화자 캐릭터와 청자 캐릭터 사이의 의사소통이고, 둘째는 영상과 관객 간의 의사소통으로 이는 첫 번째 의사소통 구조까지 모두 포함한다. 본 연구에서는 이러한 이중적 구조에 기반하여 애니메이션의 의사소통 구조를 담화내적, 담화외적 구조로 나누고, 기능적 분류법을 이용하여 캐릭터의 신체언어를 적응, 상징, 설명, 조정, 감정표현 행위로 분류하였다. 특히 본 연구의 분석 애니메이션에서 큰 비중을 차지한 설명행위는 화용론적 분류인 발화 행위론으로 세분화하였다. 그리고 분류된 각각의 신체언어를 분석하여 애니메이션에서 표현되는 신체언어의 특징을 규명하고, 효과적인 시나리오 전달과 관객의 감정이입을 도울 수 있는 효율적인 신체언어를 제안하고자 하였다.

• Asian Journal of Innovation and Policy
• /
• 제6권2호
• /
• pp.111-137
• /
• 2017

This study analyzes a language network of Science and Technology Basic Plan, which is the basis for science and technology policy in Korea, for the next Science and Technology Basic Plan. Language network analysis was adopted for a quantitative approach measuring the trend of policies. Several techniques such as keyword analysis, language network map analysis, quantitative characteristics analysis and keyword-related major-word analysis have been performed. Results show that there are common policies emphasized by all Science and Technology Basic Plans in the past, and there are also specific policies emphasized in each period of the Science and Technology Basic Plan. These specific policies come from a 'change of times' when the Science and Technology Basic Plans were established, as well as the philosophy of the national government.

• 한국영어학회지:영어학
• /
• 제4권1호
• /
• pp.61-81
• /
• 2004

This paper will look at some grammatical phenomena which will illustrate some of the questions that can be addressed with a corpus-based approach. We will use this approach to investigate the following subjects in English grammar: number ambiguity, subject-verb concord, concord with measure expressions, and (reflexive) pronoun choice in coordinated noun phrases. We will emphasize the distinctive features of the corpus-based approach, particularly its strengths in investigating language use, as opposed to traditional descriptions or prescriptions of structure in English grammar. This paper will show that a corpus-based approach has made it possible to conduct new kinds of investigations into grammar in use and to expand the scope of earlier investigations. Native speakers rarely have accurate information about frequency of use. A large representative corpus (i.e., The British National Corpus) is one of the most reliable sources of frequency information. It is important to base an analysis of language on real data rather than intuition. Any description of grammar is more complete and accurate if it is based on a body of real data.

• 아태비즈니스연구
• /
• 제7권2호
• /
• pp.61-76
• /
• 2016

This study aims to establish ways of how languages are used as determination factors for investment decisions among Asian countries where used languages are diversified. According to the analysis result, language segmentation of the investing country increases investment whereas the language segmentation of the invested countries is analyzed as the decreasing factor of investment. Also, it is analyzed that the further the linguistic distance between the investing country and the invested country the more investment increases. In the aspects of approached language distance and investment time selection, along with the increased linguistic distance, the elasticity to foreign direct investment is apprehended to be more flexible than other forms of investment. Such result shows the more segmented the languages of the targeted invested country the more investment cost will increase and therefore the results in linguistic distance can be explained as diversification of the invested country and the result to the forming of bridgehead at the invested area.

• 영어어문교육
• /
• 제13권2호
• /
• pp.129-153
• /
• 2007

When English language teachers are deciding on their priorities for teaching pronunciation, it is imperative to know what kind of differences and errors are most likely to interfere with communication, and what special problems particular first-language speakers will have with English pronunciation. In other words, phoneme discrimination skill is an integral part of speech processing for the EFL learners' learning to converse in English. Training using sound visualization technique can be effective in improving second language learners' perceptions and productions of segmental and suprasegmental speech contrasts. This study assessed the efficacy of a pronunciation training that provided visual feedback for EFL learners acquiring pitch and durational contrasts to produce and perceive English phonemic distinctions. The subjects' ability to produce and to perceive novel English words was tested in two contexts before and after training; words in isolation and words in sentences. In comparison with an untrained control group, trainees showed improved perceptual and productive performance, transferred their knowledge to new contexts, and maintained their improvement three months after training. These findings support the feasibility of learner-centered programs using sound visualization technique for English language pronunciation instruction.

• 영어어문교육
• /
• 제15권2호
• /
• pp.71-92
• /
• 2009

Europass was established in 2005 by the European Parliament and the Council of Europe as a single framework for language qualifications and competences, helping citizens to gain accreditation throughout the European Community. In addition, the 1996 Common European Framework of Reference for Languages: Learning, Teaching, Assessment (CEFR) provides a common basis for language syllabi, curriculum guidelines, examination, and textbooks in Europe. This framework describes the required knowledge and skills, the cultural context, and the levels of proficiency that learners should achieve. In combination, Europass and the CEFR provide employers and educational institutes with internationally recognized standards. This paper proposes that current trends such as globalization and international mobility require a similar approach to accreditation in Asia. As jobs and workers become independent of national boundaries and restrictions, it becomes necessary to educate students as multilingual world citizens, using standards that are accepted around the world. It is suggested, therefore, that assessment models such as Europass and the CEFR, along with successful language teaching models in Europe and Canada, present opportunities of adaptation for the Korean education system. Finally, rigorous teacher training to internationally recognized levels is recommended, if Korea is to produce a workforce of highly-skilled, plurilingual world citizens.

• 아시아태평양코퍼스연구
• /
• 제1권2호
• /
• pp.15-26
• /
• 2020

This corpus-based study investigated third language acquisition by Taiwanese college students in learning Spanish clitic pronouns at beginning and intermediate levels. It examined the acquisition sequences of Spanish clitic pronouns of the Chinese-speaking learners whose second language was English and third language was Spanish. The results indicated that indirect object pronouns (OP) preceded direct OP (case), first person preceded third person OP (person), masculine preceded feminine OP (gender), and animate preceded inanimate OP (animacy). The findings presented similar patterns as those of previous studies on English-speaking learners of Spanish. In further comparisons of the target forms in Chinese, English, and Spanish, the results suggested that L1 Chinese had strong influence on L3 Spanish, which accounts for the challenges that Taiwanese learners of Spanish face as they learn the Spanish clitic pronouns in the beginning stage.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2023년도 제35회 한글 및 한국어 정보처리 학술대회
• /
• pp.289-294
• /
• 2023

대형 언어 모델(Large Language Model)은 방대한 데이터와 파라미터를 기반으로 문맥 이해에서 높은 성능을 달성하였지만, Human Alignment를 위한 문장 생성 제어 연구는 아직 활발한 도전 과제로 남아있다. 본 논문에서는 Instruction Tuning을 통한 문장 생성 제어 실험을 진행한다. 자연어 처리 도구를 사용하여 단일 혹은 다중 제약 조건을 포함하는 Instruction 데이터 셋을 자동으로 구축하고 한국어 언어 모델인 Polyglot-Ko 모델에 fine-tuning 하여 모델 생성이 제약 조건을 만족하는지 검증하였다. 실험 결과 4개의 제약 조건에 대해 평균 0.88의 accuracy를 보이며 효과적인 문장 생성 제어가 가능함을 확인하였다.