Earticle

This paper presents a study on the introduction of User Model-Based Dialogue System. Also we present a plan-based Korean dialogue system as a natural language database user interface for product search. The system can be characterized by its support for mixed initiative to give user more control over dialogue, employment of user model to reflect user's preferences, alternative solution suggestion if there is no product matched exactly to user's requirements, handling circumlocution which frequently occurs in dialogues. The user modeling shell system BGP-MS is adapted for the system. The system provides for a user-friendly database user interface by managing dialogue intelligently. By its implementation and test, it has been shown that the user model-based dialogue system can be utilized effectively for product search.

Background: The rapid growth of the aging population has increased the demand for technologies related to muscle health, assessment, prevention, and functional support. Purpose: This study aimed to analyze technology trends in muscle-related innovations using natural language processing and machine learning applied to South Korean patent and utility model data. Study design: Descriptive study using unsupervised machine learning. Methods: A total of 2,836 records were analyzed using combined title and abstract texts. Semantic embeddings were generated using Sentence-BERT, followed by dimensionality reduction with Uniform Manifold Approximation and Projection and clustering with Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). Keywords for each cluster were extracted using term frequency-inverse document frequency, and annual filing patterns were examined to identify the trends. Results: Two dominant macro-domains were identified, including a Wearable and Sensor Technology domain (n=1,695) and a Biological and Preventive Technology domain (n=903). HDBSCAN yielded substantially better cluster validity, with a silhouette coefficient of 0.610 and Davies-Bouldin index of 0.525. Within these macro-domains, sub-domains related to stem cell and regenerative therapy, functional food and bioactive extracts, antibody and antiviral therapeutics, aging and sarcopenia mechanisms, and massage devices were identified. Conclusions: These findings provide an overview of muscle-related technology development and demonstrate the value of machine learning-based patent text analysis for technology landscape mapping and innovation assessment.

This study examined public perceptions of generative AI through the analysis of user comments on YouTube news videos regrading generative AI from three major South Korean broadcasting networks. Using structural topic modeling, 56,708 comments from 105 news videos were analyzed. Among nine distinct topics that emerged, the top three prevalent topics centered on labor market change, AI control concerns, and service automation benefits. Temporal analysis revealed evolving discourse patterns. Employment-related concerns peaked after the release of ChatGPT's but subsequently declined; three topics gained increasing prominence including human-centered AI development, control concerns, and educational applications. These findings offer theoretical and practical implications for individuals, organizations, and institutions adopting generative AI.

This paper suggests a variation of a well-known probabilistic matrix factorization algorithm which is commonly used in data analysis and scientific computing, and which has been considered recently to serve natural language processing. The proposed variation is meant to take benefit from the fact that matrices processed in natural language processing tasks are normally sparse rectangular matrices with one dimension much larger than the other, and this can be used to ensure adequate accuracy with acceptable computation time. Preliminary experiments on real-world textual corpora show that the proposed algorithm achieves relevant improvements compared to the original one.

Natural language processing, as an integral part of artificial intelligence technology, has foundations in a variety of disciplines, including linguistics, computer science, and mathematics. Rapid advances in natural language processing provide solid backing for machine translation research. This document first sets out the key concepts and key points of computational linguistics, followed by a brief review of the history and progress of NLP research in the United States and abroad. The document then summarizes the three stages of machine translation as well as the current state of research. Historically, the advancement curves of natural language processing and machine translation have almost coincided, as well as the two complement each other. On this premise, the paper examines NLP applications in machine translation and highlights problems and trends in the fields of artificial intelligence. Finally, the authors examine the link between machine translation and human interpretation in the era of artificial intelligence and speculate on machine translations long term prospects.

Vast amount of information is generated and shared in this active digital As the digital informatization is vividly going on now, most of documents are in digitalized forms, and this kind of information is on the increase. It is no exaggeration to say that this kind of newly created information and knowledge would affect the competitiveness and the future of our nation. In addition to that, a lot of investment is being made in information and knowledge based industries at national level and in reality, a lot of efforts are intensively made for research and development of human resources. It becomes easier in digital era to create and share the information as there are various tools that have been developed to create documents along with the internet, and as a result, the share of dual information is increasing day in and day out. At present, a lot of information that is provided online is actually being plagiarized or illegally copied. Specifically, it is very tricky to identify some plagiarism from tremendous amount of information because the original sentences can be simply restructured or replaced with similar words, which would make them look different from original sentences. This means that managing and protecting the knowledge start to be regarded as important, though it is important to create the knowledge through the investment and efforts. This dissertation tries to suggest new method and theory that would be instrumental in effectively detecting any infringement on and plagiarism of intellectual property of others. DICOM(Dynamic Incremental Comparison Method), a method which was developed by this research to detect plagiarism of document, focuses on realizing a system that can detect plagiarized documents and parts efficiently, accurately and immediately by creating positive and various detectors.

본 연구는 영어 원어민과 비원어민 대학생의 주장문 쓰기에서 나타나는 어휘 묶음(lexical bundle) there are so many의 의미적 운율(semantic prosody)을 분석한다. 기존 연구들이 주로 구조와 기능적 특성에 집중해온 반면, 본 연구는 담화 맥락에서 드러나는 긍·부정·중립적 의미 함의에 초점을 맞춘다. 자연어처리 기반 감성 분석을 활용하여, 두 학생 집단이 해당 어휘 묶음을 통해 어떤 입장과 태도를 드러내는지를 두 개의 비교 가능한 말뭉치를 바탕으로 분석하였다. 두 말뭉치는 각각 미국, 한국 대학생들이 작성한 영어 주장문으로 구성되어 있으며, 두 집단 모두 동일한 주제에 대해 제한된 시간 내에 글을 작성하였다. 연구 결과, 원어민 학생들은 해당 어휘 묶음을 주로 중립적이거나 긍정적인 맥락에서 사용하였으며, 이는 주로 우회적 표현이나 예시 제시에 활용되었다. 반면, 비원어민 학습자들은 이 어휘 묶음을 부정적인 맥락에서 더 자주 사용하였고, 그 결과 의미적으로 어색하거나 담화 상황에 부적절하게 사용되는 경우도 나타났다. 이러한 결과는 두 집단이 동일한 어휘 묶음을 문맥에 따라 다르게 활용한다는 점을 보여주며, 이는 담화 맥락에 적절한 표현 선택을 강조하는 글쓰기 교육이 필요함을 시사한다.

This study explores the semantic prosody of the lexical bundle (LB) there are so many in native and non-native novice English argumentative writing. While previous research on LBs has largely focused on their structural and functional patterns, this study shifts attention to their evaluative meanings in context. Using NLP-based sentiment analysis, it examines how this bundle conveys evaluative stance across two comparable corpora: one consisting of argumentative essays written by native English-speaking students and the other by Korean EFL learners. Both groups were incoming college freshmen who responded to the same prompts under identical time constraints. The results exhibited a clear difference in semantic prosody: native writers tended to use the bundle in neutral or positive contexts, often to hedge or provide examples, whereas non-native writers used it more frequently in negative contexts, which could lead to semantic incongruity or pragmatic misalignment. These findings move beyond existing accounts of LBs by highlighting the role of evaluative meaning. They suggest that L2 learners may benefit from explicit instruction on how stance is expressed in frequently occurring word sequences—an area particularly challenging for novice academic writers. This study highlights the value of sentiment-aware writing pedagogy, as informed by corpus-based insights into learner language.

Introducing the concept of construction safety in the design/planning phase can improve the efficiency and effectiveness of safety management on construction sites. In this sense, further improvements for safety can be made by designers’ involvement in the elimination or management of design-related hazards in addition to contractors’ own efforts, as known as Prevention through Design (PtD). However, this idea has not been well materialized in construction practices due in part to the lack of a PtD tool that allows designers to automatically check and evaluate designs in terms of worker safety. The paper addresses this issue by designing and testing an automated compliance checking framework that extracts information relevant to design-related hazards from regulatory documents and maps it to each of related design components using Natural Language Processing (NLP) and Building Information Modeling (BIM). The proposed framework has two key functions: 1) automatically extracting machine-readable regulation information relevant to design-related hazards using NLP techniques; and 2) automatically mapping such information to corresponding design components in a building information model, enabling the visualization of hazards. How all these components work to automatically display design-related hazards and relevant regulatory information is illustrated with a three-story building, focusing on fall protection. The proposed framework successfully extracted regulation information from textual documents with about 90% of precision and recall rates. It also correctly identified all the hazards in the case study model. The automated framework is expected to facilitate safety design review by improving designers and contractors’ proactive responses against design-related hazards

Service organizations increasingly adopt data-based intelligent engines called chatbots in support of the interaction between customers and the companies. Two different types of chatbots have been suggested and introduced by companies leading the adoption of this emerging technology: rule-based chatbots and natural language processing-based chatbots. While the differences between these two types of technologies look relatively clear, the organizational and practical impacts of the differences have not been systematically explored. This study performed an experiment to compare the use of the two different types of chatbots used in practice by two comparable organizations. These two types of actual chatbots were used by Korean on-line shopping malls with similar business models (mobile shopping), length of history, size and reputation. The comparison was made based on such dimensions as usability, searchability, reliability and attractiveness. Contraty to conventional expectation that the superiority in technology will produce superior usability, the results show mixed superiority. The discussion on the reasons is presented.

With social media growing fast, user-generated content (UGC) has become a key factor in influencing how consumers decide what to buy, especially in the travel and hospitality sector. But there are a lot of fake and extreme reviews, which are making it hard for customers to make the right choice and making competition in the market unfair. The present study focuses on YouTube, a platform with high global activity, and proposes a systematic solution that combines Natural Language Processing (NLP) and machine learning methods (e.g., VADER Sentiment Analysis, Support Vector Machine SVM, and LDA Topic Modelling) for identifying and filtering fake and extreme remarks in hotel reviews. This approach has been shown to enhance the automation and precision of review screening processes. Furthermore, it provides a theoretical foundation and practical methodologies to improve the online information ecology, thereby enhancing the quality of user decision-making.

목적: 본 연구는 “학술연구정보서비스”에서 “아시안뷰티화장품학술지”와 국내 학술지 논문 제목에서 “화장품”을 키워드로 사용 하는 학술지의 연구 논문 초록을 크롤링하여, 이들 두 집단은 과연 차별화된 정체성으로 포지셔닝되어 있으며, 어떠한 유사도와 차 이점을 가지고 있을까? 에 대한 의문으로 시작하였다. 방법: 본 연구를 수행하기 위해 Python version 3.10.9 프로그램을 이용하여 학술연구정보서비스에서 아시안뷰티화장품학술지 433편의 연구 논문과 ‘화장품’이라는 키워드로 5,232편의 연구 논문을 크롤링하 여 전처리 과정을 거쳐서 군집 분석, 공저자 네트워크 분석, 토픽 모델링 분석, 유사도 분석을 시행하였다. 결과: 두 학술지 집단은 모두 공통적으로 화장품 산업의 핵심 요소인 피부, 소비자 행동, 브랜드 전략 등 다양한 주제를 다루고 있는 것으로 나타났으나, 세 부적으로는 연구 초점이 다르게 나타났으며, 정체성이 차별화되어 있는 것으로 나타났다. 결론: 공저자 네트워크 분석에서 나타난 각 중심성 분석 결과는 연구의 시너지 효과 극대화를 위한 각 공저자의 역할과 영향력을 알 수 있었으며, 아시안뷰티화장품학술지는 비교 대상 군과는 다른 고유한 차별화된 정체성을 가지고 있는 것으로 나타났다.

Purpose: The aim of this study was to determine whether the “Asian Journal of Beauty and Cosmetology” and domestic journals that use “cosmetics” as a keyword in the abstract of their paper, are positioned with differentiated identities and to identify the similarities and differences between them. All articles were procured from the “Research Information Sharing Service.” Methods: Python version 3.10.9 was used in this study to identify 433 research papers from the “Asian Journal of Beauty and Cosmetology” and 5,232 research papers with the keyword “cosmetic” from the “Research Information Sharing Service.” After preprocessing the articles, a co-author network analysis was performed, followed by cluster analysis and topic modeling analysis. Four types of similarity analyses were performed based on the results obtained. Results: The two journal groups were found to commonly cover a variety of topics such as skin, consumer behavior, and brand strategy, that are central to the cosmetics industry. However, the research topics had different central focuses, indicating distinct identities. Conclusion: The centrality analysis results from the co-authorship network analysis revealed the roles and influence of each co-author in maximizing the synergy of research. The identity of the Asian Journal of Beauty and Cosmetology was found be unique and differentiated, compared with the comparison group.

目的: 这篇研究始于一个关于以下问题：在“学术研究信息服务”中《亚洲美容学术杂志》与国内学术期刊的论文题 目中以“化妆品”为关键词的期刊的论文摘要进行网络爬行，对这两个群体是否真正具有差异化的本质定位，他 们有哪些相同点和不同点？ 方法: 本研究使用Python 3.10.9版本识别出来自《亚洲美容与美容杂志》的433篇研 究论文以及来自“学术研究信息服务”的5,232篇关键词为“化妆品”的研究论文。对文章进行预处理后，进行合著 者网络分析，然后进行聚类分析和主题建模分析。根据获得的结果进行了四种类型的相似性分析。结果: 发现这 两个期刊组普遍涵盖了化妆品行业核心的各种主题，例如皮肤、消费者行为和品牌战略。然而，研究主题的中 心点不同，表现出不同的本性。结论: 合着网络分析的中心性分析结果揭示了每位合著者在最大化研究协同作用 中的作用和影响。与对照组相比，《亚洲美容与美容杂志》的本质是独特且有区别的。

AI (인공지능)는 알렉사와 같은 지능형 가상 비서 (IVA)을 통해서 이미 우리의 삶에 침투했으며 디자인 작업에도 도입될 가능성이 높다. 본 연구에서는 AI를 활용하여 개발될 지능형 디자인 비서에 (intelligent design assistant) 대해서, 디자이너들이 어떠한 생각을 가지고 있는지 이해하고자 한다. 이를 위해서 브라질의 UX/UI 디자이너들에게 지능형 가상 비서와 AI 디자인 도구에 관한 설문 조사를 실시했으며, 추가로 알렉사와 (Alexa) 어도비 센세이를 (Adobe Sensei) 결합하여 음성 기반 AI 디자인 비서인 알렉사 센세이를 (Alexa Sensei) 가상의 시나리오로 만든 뒤, 이에 관한 설문도 함께 실시했다. 설문조사 결과, 브라질 디자이너들은 AI와 협업할 기회는 제한되어 있었으나 AI가 디자인 프로세스의 효율성을 개선해줄 것으로 기대한다는 사실을 알아냈다. 또한 응답자의 대다수는 AI 설계 시스템과 창의적으로 협력할 수 있을 것이라고 예측했다. 자연어를 통한 의사소통에는 한계가 있을 것으로 바라보았지만, 이미 지능형 가상 비서를 사용한 경험이 있는 디자이너들은 음성 기반 AI 디자인 비서에 대한 거부감이 낮다는 점도 함께 밝혀졌다.

Artificial Intelligence (AI) has been inserted into people’s lives through Intelligent Virtual Assistants (IVA), like Alexa. Moreover, intelligent systems have expanded to design studios. This research delves into designers’ perspectives on developing AI-based practices and examines the challenges of adopting future intelligent design assistants. We surveyed UX/UI professionals in Brazil to understand how they use IVAs and AI design tools. We also explored a scenario featuring the use of Alexa Sensei, a hypothetical voice-controlled AI-based design assistant mixing Alexa and Adobe Sensei characteristics. The findings indicate respondents have had limited opportunities to work with AI, but they expect intelligent systems to improve the efficiency of the design process. Further, majority of the respondents predicted that they would be able to collaborate creatively with AI design systems. Although designers anticipated challenges in natural language interaction, those who already adopted IVAs were less resistant to the idea of working with Alexa Sensei as an AI design assistant.

성폭력 사건의 수사 및 재판 단계에서 피해자 진술의 신빙성 판단이 중요해짐에 따라 진술분석의 수요가 증가하고 있다. 피해자 진술의 일관성은 진술 신빙성 판단의 주요 기준 중 하나이다. 4차 산업혁명 시대에 점차 고도화되는 자연어처리 기술은 대화 내용을 분석하는데 확장되고 있는 점에 착안하여, 이 연구는 자연어 처리 기술인 Triple+ 추출을 적용한 진술 일관성 분석의 정확도를 확인고자 하였다. 이를 위해 진술분석 교육을 이수한 평가자가 57건의 실제 피해자 진술 녹취록에 대해 진술 일관성 분석을 실시한 후 Triple+를 이용한 진술 불일치 분석 결과와 비교하였다. 평가자의 분석 결과 확인된 18쌍의 비일관적인 문장들에 대한 Triple+를 추출하고 7가지 진술 불일치 유형으로 구분하였으며 유형별 진술 불일치 판단 규칙을 설정하였다. 분석 결과, Triple+가 평균적으로 77% 정확하게 진술 불일치를 판별하는 것으로 나타났다. 세부 유형별로는, 방향, 시점, 행동 주체 유형은 100%, 내용 부정 유형은 75%, 장소 유형은 66.7%, 사건의 순서, 피동․능동 유형 판별은 50%의 정확도로 나타났다. 또한, 무작위로 선정된 32쌍의 일관적인 문장에 대한 판단에서는 93.8%의 판별 정확도를 보였다. 이러한 연구 결과는 Triple+을 이용한 자동적 진술 불일치 판별은 진술분석의 보조도구로서 효율성을 높일 수 있을 것으로 기대된다. 인공지능 진술분석에 필요한 현존하는 자연어 처리 기술의 한계와 향후 연구의 방향에 대해서도 논의하였다.

Demand for statement analysis is increasing as the credibility of the victim's statement becomes more important in the investigation and trial of sexual offence cases. The consistency of the victim's statement is one of the main criteria for judging the credibility of a victim. In the era of 4th industrial revolution natural language processing technology is rapidly growing to analyze conversation contents. This study tried to verify the accuracy of statement consistency analysis using Triple+ extractions, a natural language processing technology. Trained evaluators conducted a statement consistency analysis on 57 actual transcripts of victim statements and compared them with the results of statement inconsistency analysis using Triple+. The Triple+ for 18 pairs of inconsistent sentences from victim statements were extracted and classified into 7 types of statement inconsistency. The rules of determining statement inconsistency for each type were established. The results showed that Triple+ correctly identified statement discrepancies 77% on the average. For subtypes of inconsistency classification accuracy varied as 100% for the direction, timing, and action, 75% for content denial, 66.7% for place, and 50% accuracy of event sequence and passive/active type were found. 93.8% accuracy was achieved in the judgment of 32 randomly selected pairs of consistent sentences. The results of this study suggest a potential for automatic statement inconsistency discrimination using Triple+ as supplementary tool for human expert statement analysis. The limitations of the existing natural language processing technology required for artificial intelligence statement analysis and the direction of future research are discussed.

광업기본계획에 대한 텍스트 데이터 분석으로 기존의 전문가 분석 방법과 다른 정량적인 분석 결과를 보여줄 수 있다. 2014년 제2차, 2020년 제3차, 2024년 제4차로 발표된 광업기본계획에 대한키워드 및 주제 구조 변화를 정량적으로 분석하였다. 자연어처리 기반 단어 빈도 분석과 토픽모델링 분석으로 광업기본계획 간 공통점과 차이점을 탐색하였다. 제2차 광업기본계획은 계획·전략수립에 대한 기반 정책 측면의 결과가 나타났으며, 제3차 광업기본계획은 안전·교육·소재·북한으로 키워드 및 주제가 확대되었다. 제4차 광업기본계획은 글로벌 원자재 공급망 불안 확대를 나타내는 비축 키워드와 함께 외국인고용·스마트마이닝 주제가 부각되었다. 본 연구는 자연어처리 기반 토픽모델링을 통해 시간 변화에 따른 주제 및 키워드의 진화 양상을 체계적으로 도출한 의의가있다.

Text data analysis of Basic Mining Plans can yield quantitative results that differ from those obtained through expert analysis methods. This study conducted a quantitative analysis of the changes in the following Basic Mining Plans: the 2nd Plan in 2014, the 3rd Plan in 2020, and the 4th Plan in 2024. The commonalities and differences among these plans were examined through word frequency and topic modeling analyses based on natural language processing techniques. The 2nd Basic Mining Plan emphasized planning and strategy development, while the 3rd Plan expanded to include safety, education, materials, and issues related to North Korea. The 4th Plan highlighted the topics of foreign employment and smart mining, along with the stockpiling keyword, which indicates an increase in instability within the global raw material supply chain. This study systematically traced the evolution of topics and keywords over time through topic modeling based on natural language processing.

본 연구는 한국어 습득 아동의 증거성표지 습득 양상을 검토하고자 한 아동의 자료를 중심으로 자발적 산출의 양상을 검토하고, 어머니의 관련 입력 언어를 분석하였다. 특히, 만 2-3세에 주로 산출되는 증거성표지와 정보 출처 관련 어휘를 검토하였고, 어머니의 입력 언어에서 관련 표현들의 빈도 분석을 실시하여 입력언어와의 관계를 살펴보았다. 또한 한국어와 유사한 일본 아동과 양육자의 관련 자료를 비교 분석하여 언어 간 입력 언어 차이에 따른 산출 양상도 비교, 분석하였다. 자발적 산출 분석 결과 직접 경험을 나타내는 표지 및 어휘의 사용이 간접 경험이나 보고의 표지보다 양육자와 아동 모두에게서 높았으며, 한국과 일본의 ‘대’, ‘보다’, ‘듣다’ 사용 빈도를 비교한 결과 한국 양육자가 일본 양육자에 비해 어휘 사용이 상대적으로 높고, 형태소 사용 빈도가 상대적으로 낮은 것으로 나타났다. 비록 제한된 자료들의 검토이나 이러한 결과는 증거성표지나 관련 어휘의 습득이 인식론적으로 보다 직접적인 것에서 간접적인 것의 순서로 이루어지고 있음을 시사하며, 인식론적 상태에 따라 화자가 전달하는 정보의 확실성이 달라진다는 것을 이해하게 되는 시기와도 관련이 있음을 시사한다.

The purpose of the current study was to investigate the developmental pattern of evidential markers and related verbs by examining the child’s natural production and mother’s input language. First, two audio-recorded corpora of Korean mother-child dyad’s natural production were analyzed for frequency, age of emergence and productive use of evidential markers and related verbs. Also, the result of the corpora analyses was directly compared to one Japanese mother-child dyad’s recorded speech corpus. The analyses of natural production revealed that children begin using direct experience marker/verb before hearsay or inference markers/verbs. Furthermore, mother’s input pattern appeared to be aligned with the child’s use of these markers/verbs. These findings suggest that the acquisition of evidential markers and related verbs proceed from those that describe direct experience to hearsay or indirect inference or conjecture, implying that such order of acquisition might play a role in the later development of information certainty judgments on the basis of evidentiality.

대화시스템에서 자연어 생성은 대화관리 단계에서 결정한 시스템 발화의 의미표현을 사람이 이해할 수 있는 자연어 로 생성하는 것이다. 기존의 자연어 생성 연구는 의미표현에 대하여 매우 제한된 종류의 발화만을 생성하거나 문법 적으로 불완전한 발화를 생성한다는 문제점이 있다. 그래서 본 논문에서는 문제점들을 동시에 처리하기 위하여 Long Short Term Memory 기반의 언어모델을 이용한 한국어 자연어 생성 모델을 제안한다. 특히 우리는 시스템 발화의 다양성과 문법적 정확성을 높이기 위하여 빔서치 디코딩을 적용한다. 실험은 어절, 형태소, 음절단위에 따라 개별적으로 진행하였으며, 생성한 문장들은 정량적, 정성적 평가를 모두 진행하였다. 그 결과 형태소 단위로 학습한 제안모델에 빔서치 디코딩을 적용한 방법은 가장 좋은 성능을 보였다. 실제로 해당 생성 문장은 정량평가 결과에서 BLEU 지표는 0.86, Slot Error Rate 지표는 0.03을 기록하였으며 정성평가 역시 문법적으로 정확하고 문맥적 으로 충분히 자연스러운 결과임을 확인하였다.

Natural language generation in the dialogue system is a task that transforms the semantic frame of the system utterance determined in the dialogue management phase into a natural language that can be understood by humans. Existing studies have still faced some obstacles in that only very limited types of utterances or grammatically incomplete ones are generated from the semantic frames. In order to address these issues simultaneously, we propose a Korean natural language generation model using a long short term memory based language model. In particular, we exploit the beam search decoding method to obtain system utterances with diverse structures and grammatical correctness. The experiments were conducted individually with respect to the word, morpheme, and syllable units, and the generated utterances were evaluated in both quantitative and qualitative ways. As a result, the morpheme-based model with the beam search decoding has achieved the most robust result of all. In fact, in the quantitative evaluation result of the generated sentence, the BLEU-4 score was 0.86 and the SER was 0.03, and the qualitative evaluation was also confirmed to be grammatically correct and contextually natural.

This study reviews two opposing theories regarding human language competence, i.e. the logical nativism vs. empiricism, which is reminiscent of the so-called ‘nature vs. nurture’ dispute originating from Plato’s dialogues. Generative grammar is the representative linguistic theory that embodies the idea of logical nativism, whereas Constructivist theory is the typical experience-based linguistic approach. Connectionist model (deep learning), the leading methodology of current NLP(natural language processing), is reconsidered with respect to the two theories of language competence aforementioned and the empirical nature of deep learning devise is confirmed. By reviewing possibilities and limitations of integration of the empirical approach of connectionism and the rule-based approach of theoretical linguistics discussed by Pater (2019) and others, it is concluded that a hybrid approach is in need. Two additional factors supporting the hybrid approach are provided, one for a proper explanation of the difference between native language acquisition and foreign language acquisition and the other from the empirical nature incorporated in Montague semantics which is fundamentally a rule-based linguistic theory.