• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.912-915
• /
• 2020

최근 자연어 처리 기술은 지속적으로 발전하고 있으며, 많은 분야에서 활용되고 있다. 그 중 번역 기술은 가장 널리 사용되고 있는 자연어 처리 기술 중 하나이다. 본 논문에서는 기존의 seq2seq 모델의 단점을 극복하기 위해 개발된 Transformer 를 통해 영어-한국어 번역기를 만드는 것의 가능성을 제시한다.

• The Magazine of the IEIE
• /
• v.24 no.9
• /
• pp.83-90
• /
• 1997

• Digital Contents
• /
• no.7 s.38
• /
• pp.24-28
• /
• 1996

• TTA Journal
• /
• s.169
• /
• pp.33-37
• /
• 2017

• Korean Journal of Construction Engineering and Management
• /
• v.21 no.6
• /
• pp.125-134
• /
• 2020

Natural language encountered in construction documents largely deviates from those that are recommended by the authorities. Such practice that is lacking in coherence will discourage integrated research with automation, and it will hurt the productivity in the industry for the long run. This research aims to compare multiple string similarity (string matching) algorithms to compare each algorithm's performance in recognizing the same task name written in multiple different ways. We also aim to start a debate on how prevalent the aforementioned deviation is. Finally, we composed a small dataset that associates construction task names found in practice with the corresponding task names that are less cluttered w.r.t their formatting. We expect that this dataset can be used to validate future natural language processing approaches.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.5
• /
• pp.1035-1041
• /
• 2004

Currently users are tend to use multimedia data types in their applications. Main features of multimedia data types are large amount of data compared to conventional data types. In this reason, it's hard to load data into main memory and to search. That is the cause of occur disk input and output frequently, and decrease the system performance. In this paper, we describe to have fast and efficient access to multimedia data using index technique. Index method presented by paper consists of two parts : one is index file part for keywords and the other is posting file part for the list of file names. Of course, we use keyword. But user is not charge of memory for the keywords. Users just use natural language to insert, delete and search data what he or she wants. Internally, System makes keywords from natural language to get access to multimedia data. It provides convenience to users. Using this study to develop one's application for multimedia, one may have a chance for advanced performance of a system and getting a result speedily.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.4
• /
• pp.145-152
• /
• 2020

MRC (Machine reading comprehension) is the AI NLP task that predict the answer for user's query by understanding of the relevant document and which can be used in automated consult services such as chatbots. Recently, the BERT (Pre-training of Deep Bidirectional Transformers for Language Understanding) model, which shows high performance in various fields of natural language processing, have two phases. First phase is Pre-training the big data of each domain. And second phase is fine-tuning the model for solving each NLP tasks as a prediction. In this paper, we have made the Patent MRC dataset and shown that how to build the patent consultation training data for MRC task. And we propose the method to improve the performance of the MRC task using the Pre-trained Patent-BERT model by the patent consultation corpus and the language processing algorithm suitable for the machine learning of the patent counseling data. As a result of experiment, we show that the performance of the method proposed in this paper is improved to answer the patent counseling query.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.8
• /
• pp.331-342
• /
• 2019

This paper proposes a method to generate test cases and test scripts from software requirements written in a controlled natural language, which helps develop reliable embedded software. In the proposed method, natural language requirements are written in a controlled language, the requirements are parsed and then inputs, outputs and operator data are extracted from the requirements. Test cases are generated from the extracted data following test case generation strategies such as decision coverage, condition coverage or modified condition/decision coverage. And then the test scripts, physical inputs of the test cases are generated with help of the test command dictionary. With the proposed method, it becomes possible to directly check whether software properly satisfies the requirements. Effectiveness of the proposed method is verified empirically with an requirement set.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.333-335
• /
• 2022

본 논문에서는 기존에 두 가지 모델이 필요했던 작업을 하나의 모델로 처리할 수 있는 자연어 처리 아키텍처를 제안한다. 단일 모델로 알츠하이머 환자의 언어패턴과 대화맥락을 분석하고 두 가지 결과인 환자분류와 챗봇의 대답을 도출한다. 일상생활에서 챗봇으로 환자의 언어특징을 파악한다면 의사는 조기진단을 위해 더 정밀한 진단과 치료를 계획할 수 있다. 제안된 모델은 전문가가 필요했던 질문지법을 대체하는 챗봇 개발에 활용된다. 모델이 수행하는 자연어 처리 작업은 두 가지이다. 첫 번째는 환자가 병을 가졌는지 여부를 확률로 표시하는 '자연어 분류'이고 두 번째는 환자의 대답에 대한 챗봇의 다음 '대답을 생성'하는 것이다. 전반부에서는 셀프어탠션 신경망을 통해 환자 발화 특징인 맥락벡터(context vector)를 추출한다. 이 맥락벡터와 챗봇(전문가, 진행자)의 질문을 함께 인코더에 입력해 질문자와 환자 사이 상호작용 특징을 담은 행렬을 얻는다. 벡터화된 행렬은 환자분류를 위한 확률값이 된다. 행렬을 챗봇(진행자)의 다음 대답과 함께 디코더에 입력해 다음 발화를 생성한다. 이 구조를 DementiaBank의 쿠키도둑묘사 말뭉치로 학습한 결과 인코더와 디코더의 손실함수 값이 유의미하게 줄어들며 수렴하는 양상을 확인할 수 있었다. 이는 알츠하이머병 환자의 발화 언어패턴을 포착하는 것이 향후 해당 병의 조기진단과 종단연구에 기여할 수 있음을 보여준다.

• Journal of Korean Society of Archives and Records Management
• /
• v.24 no.2
• /
• pp.65-88
• /
• 2024

This pilot study explores a method of extracting metadata values and descriptions from records using named entity recognition (NER), a technique in natural language processing (NLP), a subfield of artificial intelligence. The study focuses on handwritten records from the Guro Industrial Complex, produced during the 1960s and 1970s, comprising approximately 1,200 pages and 80,000 words. After the preprocessing process of the records, which included digitization, the study employed a publicly available language API based on Google's Bidirectional Encoder Representations from Transformers (BERT) language model to recognize entity names within the text. As a result, 173 names of people and 314 of organizations and institutions were extracted from the Guro Industrial Complex's past records. These extracted entities are expected to serve as direct search terms for accessing the contents of the records. Furthermore, the study identified challenges that arose when applying the theoretical methodology of NLP to real-world records consisting of semistructured text. It also presents potential solutions and implications to consider when addressing these issues.