• 한국IT서비스학회지
• /
• 제21권2호
• /
• pp.61-84
• /
• 2022

With the recent application of deep learning to Natural Language Processing (NLP), the performance of NLP has improved significantly and NLP is emerging as a core competency of organizations. However, when encountering NLP use cases that are sporadically reported through various online and offline channels, it is often difficult to come up with a big picture of how to understand and interpret them or how to connect them to business. This study presents a framework for systematically analyzing NLP use cases, considering the characteristics of NLP techniques applicable to almost all industries and business functions, environmental changes in the era of the Fourth Industrial Revolution, and the effectiveness of adopting NLP reflecting all business functional areas. Through solving research questions based on the framework, the usefulness of it is validated. First, by accumulating NLP use cases and pivoting them around the business function dimension, we derive how NLP techniques are used in each business functional area. Next, by synthesizing related surveys and reports to the accumulated use cases, we draw implications for each business function and major NLP techniques. This work promotes the creation of innovative business scenarios and provides multilateral implications for the adoption of NLP by systematically viewing NLP techniques, industries, and business functional areas. The use case analysis framework proposed in this study presents a new perspective for research on new technology use cases. It also helps explore strategies that can dramatically improve organizational performance through a holistic approach that encompasses all business functional areas.

• 한국언어정보학회지:언어와정보
• /
• 제15권2호
• /
• pp.23-45
• /
• 2011

This paper proposes a statistical-based linguistic methodology for automatic mapping between large-scale heterogeneous languages resources for NLP applications in general. As a particular case, it treats automatic mapping between two large-scale heterogeneous Korean language resources: Sejong Semantic Classes (SJSC) in the Sejong Electronic Dictionary (SJD) and nouns in KorLex. KorLex is a large-scale Korean WordNet, but it lacks syntactic information. SJD contains refined semantic-syntactic information, with semantic labels depending on SJSC, but the list of its entry words is much smaller than that of KorLex. The goal of our study is to build a rich language resource by integrating useful information within SJD into KorLex. In this paper, we use both linguistic and statistical methods for constructing an automatic mapping methodology. The linguistic aspect of the methodology focuses on the following three linguistic clues: monosemy/polysemy of word forms, instances (example words), and semantically related words. The statistical aspect of the methodology uses the three statistical formulae ${\chi}^2$, Mutual Information and Information Gain to obtain candidate synsets. Compared with the performance of manual mapping, the automatic mapping based on our proposed statistical linguistic methods shows good performance rates in terms of correctness, specifically giving recall 0.838, precision 0.718, and F1 0.774.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권1호
• /
• pp.391-406
• /
• 2015

Social media have emerged as new communication channels between consumers and companies that generate a large volume of unstructured text data. This social media content, which contains consumers' opinions and interests, is recognized as valuable material from which businesses can mine useful information; consequently, many researchers have reported on opinion-mining frameworks, methods, techniques, and tools for business intelligence over various industries. These studies sometimes focused on how to use opinion mining in business fields or emphasized methods of analyzing content to achieve results that are more accurate. They also considered how to visualize the results to ensure easier understanding. However, we found that such approaches are often technically complex and insufficiently user-friendly to help with business decisions and planning. Therefore, in this study we attempt to formulate a more comprehensive and practical methodology to conduct social media opinion mining and apply our methodology to a case study of the oldest instant noodle product in Korea. We also present graphical tools and visualized outputs that include volume and sentiment graphs, time-series graphs, a topic word cloud, a heat map, and a valence tree map with a classification. Our resources are from public-domain social media content such as blogs, forum messages, and news articles that we analyze with natural language processing, statistics, and graphics packages in the freeware R project environment. We believe our methodology and visualization outputs can provide a practical and reliable guide for immediate use, not just in the food industry but other industries as well.

• Genomics & Informatics
• /
• 제19권3호
• /
• pp.22.1-22.5
• /
• 2021

Automatic document classification for highly interrelated classes is a demanding task that becomes more challenging when there is little labeled data for training. Such is the case of the coronavirus disease 2019 (COVID-19) clinical repository-a repository of classified and translated academic articles related to COVID-19 and relevant to the clinical practice-where a 3-way classification scheme is being applied to COVID-19 literature. During the 7th Biomedical Linked Annotation Hackathon (BLAH7) hackathon, we performed experiments to explore the use of named-entity-recognition (NER) to improve the classification. We processed the literature with OntoGene's Biomedical Entity Recogniser (OGER) and used the resulting identified Named Entities (NE) and their links to major biological databases as extra input features for the classifier. We compared the results with a baseline model without the OGER extracted features. In these proof-of-concept experiments, we observed a clear gain on COVID-19 literature classification. In particular, NE's origin was useful to classify document types and NE's type for clinical specialties. Due to the limitations of the small dataset, we can only conclude that our results suggests that NER would benefit this classification task. In order to accurately estimate this benefit, further experiments with a larger dataset would be needed.

• 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.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제33권12호
• /
• pp.1073-1089
• /
• 2006

자연언어처리의 목적은 컴퓨터가 자연어를 이해할 수 있도록 하여, 인간에게 다양한 정보를 정확하고 빠르게 전달할 수 있도록 하고자 하는 것이다. 이를 위해서는 언어의 의미를 정확히 파악하여야 하는데, 어휘 의미 중의성 해소가 필수적인 기술이다. 본 연구는 상호정보량과 기 분석된 복합명사 의미사전에 기반한 동음이의어 의미 중의성 해소를 위한 기술을 소개한다. 사전 뜻풀이를 이용하는 기존 기술들은 어휘들간의 정확한 매칭에 의존하기 때문에 자료 부족 현상이 심각하였다. 그러나, 본 연구에서는 어휘들간의 연관계수인 상호정보량을 이용함으로써 이 문제를 완화시켰다. 또한, 언어적인 특징을 반영하기 위해서 상호정보량을 가지는 어휘 쌍의 비율 가중치, 의미 별 비율 가중치와 뜻풀이의 길이 가중치를 사용하였다. 그리고, 복합명사를 구성하는 단일명사들은 서로의 의미를 제약한다는 것에 기반하여 고빈도 복합명사에 대해서 의미를 부착한 의미사전을 구축하였고, 이를 동음이의어 중의성 해소에 활용하였다. 본 시스템의 평가를 위해 질의응답 평가셋의 200 여 개의 질의와 정답단락을 대상으로 동음이의어 의미 중의성 해소 평가셋을 구축하였다. 평가셋에 기반하여 네 유형의 실험을 수행하였다. 실험 결과는 상호 정보량만을 이용하였을 때 65.06%의 정확률을 보였고, 가중치를 활용하였을 때 85.35%의 정확률을 보였다. 또한, 복합명사 의미분석 사전을 활용하였을 때는 88.82%의 정확률을 보였다.

• 지능정보연구
• /
• 제20권4호
• /
• pp.89-105
• /
• 2014

Web2.0의 등장과 함께 급속히 발전해온 온라인 포럼, 블로그, 트위터, 페이스북과 같은 소셜 미디어 서비스는 소비자와 소비자간의 의사소통을 넘어 이제 기업과 소비자 사이의 새로운 커뮤니케이션 매체로도 인식되고 있다. 때문에 기업뿐만 아니라 수많은 기관, 조직 등에서도 소셜미디어를 활용하여 소비자와 적극적인 의사소통을 전개하고 있으며, 나아가 소셜 미디어 콘텐츠에 담겨있는 소비자 고객들의 의견, 관심, 불만, 평판 등을 분석하고 이해하며 비즈니스에 적용하기 위해 이를 적극 분석하는 단계로 진화하고 있다. 이러한 연구의 한 분야로서 비정형 텍스트 콘텐츠와 같은 빅 데이터에서 저자의 감성이나 의견 등을 추출하는 오피니언 마이닝과 감성분석 기법이 소셜미디어 콘텐츠 분석에도 활발히 이용되고 있으며, 이미 여러 연구에서 이를 위한 방법론, 테크닉, 툴 등을 제시하고 있다. 그러나 아직 대량의 소셜미디어 데이터를 수집하여 언어처리를 거치고 의미를 해석하여 비즈니스 인사이트를 도출하는 전반의 과정을 제시한 연구가 많지 않으며, 그 결과를 의사결정자들이 쉽게 이해할 수 있는 시각화 기법으로 풀어내는 것 또한 드문 실정이다. 그러므로 본 연구에서는 소셜미디어 콘텐츠의 오피니언 마이닝을 위한 실무적인 분석방법을 제시하고 이를 통해 기업의사결정을 지원할 수 있는 시각화된 결과물을 제시하고자 하였다. 이를 위해 한국 인스턴트 식품 1위 기업의 대표 상품인 N-라면을 사례 연구의 대상으로 실제 블로그 데이터와 뉴스를 수집/분석하고 결과를 도출하였다. 또한 이런 과정에서 프리웨어 오픈 소스 R을 이용함으로써 비용부담 없이 어떤 조직에서도 적용할 수 있는 레퍼런스를 구현하였다. 그러므로 저자들은 본 연구의 분석방법과 결과물들이 식품산업뿐만 아니라 타 산업에서도 바로 적용 가능한 실용적 가이드와 참조자료가 될 것으로 기대한다.