Browse > Article
http://dx.doi.org/10.36498/kbigdt.2021.6.1.63

Analysis of the Status of Natural Language Processing Technology Based on Deep Learning  

Park, Sang-Un (경기대학교)
Publication Information
The Journal of Bigdata / v.6, no.1, 2021 , pp. 63-81 More about this Journal
Abstract
The performance of natural language processing is rapidly improving due to the recent development and application of machine learning and deep learning technologies, and as a result, the field of application is expanding. In particular, as the demand for analysis on unstructured text data increases, interest in NLP(Natural Language Processing) is also increasing. However, due to the complexity and difficulty of the natural language preprocessing process and machine learning and deep learning theories, there are still high barriers to the use of natural language processing. In this paper, for an overall understanding of NLP, by examining the main fields of NLP that are currently being actively researched and the current state of major technologies centered on machine learning and deep learning, We want to provide a foundation to understand and utilize NLP more easily. Therefore, we investigated the change of NLP in AI(artificial intelligence) through the changes of the taxonomy of AI technology. The main areas of NLP which consists of language model, text classification, text generation, document summarization, question answering and machine translation were explained with state of the art deep learning models. In addition, major deep learning models utilized in NLP were explained, and data sets and evaluation measures for performance evaluation were summarized. We hope researchers who want to utilize NLP for various purposes in their field be able to understand the overall technical status and the main technologies of NLP through this paper.
Keywords
NLP; machine learning; deep learning; data set; evaluation measures;
Citations & Related Records
연도 인용수 순위
  • Reference
1 민재옥, 박진우, 조유정, 이봉건, "BERT를 이용한 한국어 특허상담 기계독해", 정보처리학회논문지, Vol. 9, No. 4, pp. 145-152, 2020.   DOI
2 곽현, 전성태, 박성혁, 석왕헌, "인공지능(AI) 기술 및 정책 동향", 2016 지식재산 이슈페이퍼, 한국지식재산연구원, pp. 35-76, 2016.
3 Yang, Wei, et al., "End-to-end open-domain question answering with BERTserini." arXiv preprint arXiv:1902.01718, 2019.   DOI
4 특허청, "4차 산업혁명 기술체계(Tech Tree)", 2018.
5 Sutskever, Ilya, Oriol Vinyals, and Quoc V. Le, "Sequence to sequence learning with neural networks", Advances in neural information processing systems, 2014.
6 Radford, Alec, et al., "Improving language understanding by generative pre-training", 2018.
7 이상아, 장한솔, 백연미, 박수지, 신효필, "소규모 데이터 기반 한국어 버트 모델", 정보과학회논문지, Vol. 47, No. 7, pp. 682-692, 2020.
8 Brown, Tom B., Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan et al., "Language models are few-shot learners", arXiv preprint arXiv:2005.14165, 2020.
9 김선우, 최성필, "Bidirectional LSTM-CRF 기반의 음절 단위 한국어 품사 태깅 및 띄어쓰기 통합 모델 연구", 정보과학회논문지, Vol. 45, No. 8, pp. 792-800, 2018.
10 Waltz, David L., "Evolution, Sociobiology, and the future of artificial intelligence", IEEE Intelligent Systems, Vol. 21, No. 3, pp. 66-69, 2006.   DOI
11 특허청, "4차 산업혁명 관련 기술 특허통계집", 2020.
12 Adhikari, Ashutosh, et al., "Docbert: Bert for document classification", arXiv preprint arXiv: 1904.08398, 2019.
13 오영택, 김민태, 김우주. "Parallel Stacked Bidirectional LSTM 모델을 이용한 한국어 영화 리뷰 감성 분석", 정보과학회논문지, Vol. 46, No. 1, pp. 45-49, 2019.
14 이승현, 장동표, 성강경, "자연어 처리 및 기계학습을 통한 동의보감 기반 한의변증진단 기술 개발", 대한한의학회지, Vol. 41, No. 3, pp. 1-8, 2020.   DOI
15 김용기, 이창희, 이정민, "쇼핑몰 지능형 챗봇의 자연어 처리를 위한 패션쇼핑 개체명 인식 사전 구축", 한국경영과학회 학술대회논문집, pp. 2744-2749, 2018.
16 Vaswani, Ashish, et al., "Attention is all you need." Advances in neural information processing systems, pp. 5998-6008, 2017.
17 Brown, Tom B., et al., "Language models are few-shot learners", arXiv preprint arXiv:2005.14165, 2020.
18 Devlin, 2018, Jacob, et al., "Bert: Pre-training of deep bidirectional transformers for language understanding", arXiv preprint arXiv:1810.04805, 2018.
19 장동진, Ubaid Ur Rehman, 정윤혜, Hafiz Syed Muhammad Bilal, 이승룡, "자연어처리 기반 진화형 임상의사결정지원시스템: 녹내장 진단 사례연구", 한국통신학회지(정보와통신), Vol. 37, No. 9, pp. 34-39, 2020.
20 조병선, 이석원, "자연어처리와 기계학습을 이용한 요구사항 분석기술 비교 연구", 한국컴퓨터정보학회논문지, Vol. 25, No. 7, pp. 27-37, 2020.
21 Russell, Stuart, and Peter Norvig, "Artificial intelligence: a modern approach third edition", 2016.
22 양희태, 최병삼, 이제영, 장훈, 백서인, 김단비, "인공지능 기술 전망과 혁신정책 방향", 과학기술정책연구원, 2018.
23 과학기술일자리진흥원, "인공지능(빅데이터) 시장 및 기술동향", 2019.
24 https://scikit-learn.org/stable/tutorial/machine_learning_map/index.html
25 박영민, 김학수, "음성 대화 시스템을 위한 심층 학습 기반 자연어 생성 기술", 정보과학회지, Vol. 39, No. 4, pp. 39-45, 2021.
26 Zhang, Haoyu, Jianjun Xu, and Ji Wang, "Pretraining-based natural language generation for text summarization", arXiv preprint arXiv: 1902.09243, 2019.
27 김영민, 임승영, 이현정, 박소윤, 김명지, "KorQuAD 2.0: 웹문서 기계독해를 위한 한국어 질의응답 데이터셋", 정보과학회논문지, Vol. 47, No. 6, pp. 577-586, 2020.
28 Medina, Julian Richard, and Jugal Kalita, "Parallel attention mechanisms in neural machine translation", 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), 2018.
29 Yoon Kim, "Convolutional neural networks for sentence classification", arXiv preprint arXiv: 1408.5882, 2014.
30 Bahdanau, Dzmitry, Kyunghyun Cho, and Yoshua Bengio, "Neural machine translation by jointly learning to align and translate", arXiv preprint arXiv:1409.0473, 2014.