기술 용어에 대한 한국어 정의 문장 자동 생성을 위한 순환 신경망 모델 활용 연구 (Research on the Utilization of Recurrent Neural Networks for Automatic Generation of Korean Definitional Sentences of Technical Terms)

최가람; 김한국 (Hangook Kim); 김광훈 (Kim， Kwang-Hoon); 김유일; 최성필 (Sung-Pil Choi)

doi:10.4275/KSLIS.2017.51.4.099

Research on the Utilization of Recurrent Neural Networks for Automatic Generation of Korean Definitional Sentences of Technical Terms

Journal of the Korean Society for Library and Information Science
2017, 51(4), pp.99-120
DOI : 10.4275/KSLIS.2017.51.4.099
Publisher : 한국문헌정보학회
Research Area : Interdisciplinary Studies > Library and Information Science

최가람 ¹, Hangook Kim ², Kim， Kwang-Hoon ², 김유일 ², Sung-Pil Choi ¹

¹경기대학교
²한국과학기술정보연구원

Accredited

ABSTRACT

In order to develop a semiautomatic support system that allows researchers concerned to efficiently analyze the technical trends for the ever-growing industry and market. This paper introduces a couple of Korean sentence generation models that can automatically generate definitional statements as well as descriptions of technical terms and concepts. The proposed models are based on a deep learning model called LSTM (Long Sort-Term Memory) capable of effectively labeling textual sequences by taking into account the contextual relations of each item in the sequences. Our models take technical terms as inputs and can generate a broad range of heterogeneous textual descriptions that explain the concept of the terms. In the experiments using large-scale training collections, we confirmed that more accurate and reasonable sentences can be generated by CHAR-CNN-LSTM model that is a word-based LSTM exploiting character embeddings based on convolutional neural networks (CNN). The results of this study can be a force for developing an extension model that can generate a set of sentences covering the same subjects, and furthermore, we can implement an artificial intelligence model that automatically creates technical literature.

KEYWORDS

Sentence Generation, Text Generation, Natural Language Generation(NLG), Automatic Report Generation, Deep Learning

Citation status

* References for papers published after 2023 are currently being built.

[confproc] Bahdanau, D. / 2014 / Neural Machine Translation by Jointly Learning to Align and Translate / conference ICLR 2015

[confproc] Bauer, A. / 2015 / Rule-based Approach to Text Generation in Natural Language-Automated Text Markup Language (ATML3) / Challenge+ DC@RuleML 2015

[confproc] Bian, J. / 2014 / Knowledge-powered Deep Learning for Word Embedding / Joint European Conference on Machine Learning and Knowledge Discovery in Databases : 132~148

[confproc] Bontcheva, K. / 2004 / Automatic Report Generation from Ontologies : the MIAKT Approach / International Conference on Application of Natural Language to Information Systems : 324~335

[confproc] Boulanger-Lewandowski, N. / 2012 / Modeling Temporal Dependencies in High-dimensional Sequences: Application to Polyphonic Music Generation and Transcription / Proceedings of the Twenty-nine International Conference on Machine Learning ICML

[confproc] Bowman, S. / 2016 / Generating Sentences from a Continuous Space / SIGNLL Conference on Computational Natural Language Learning (CONLL) : 2016~

[journal] Deng, L. / 2014 / Deep Learning: Methods and Applications / Foundations and Trends® in Signal Processing 7(3-4) : 197~387

[confproc] Graves, A. / 2013 / Hybrid Speech Recognition with Deep Bidirectional LSTM. In Automatic Speech Recognition and Understanding(ASRU) / 2013IEEE Workshop on : 273~278

[thesis] Hochreiter, S. / 1991 / Untersuchungen zu Dynamischen Neuronalen Netzen / Ph.D. / Institut fur Informatik, Technische Universitat

[journal] Hochreiter, S. / 1997 / Long Short-Term Memory. Neural Computation / Neural Computation 9(8) : 1735~1780

[confproc] Kalchbrenner, N. / 2014 / A Convolutional Neural Network for Modelling Sentences / Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics : 655~665

[journal] Krizhevsky, A. / 2012 / Imagenet Classification with Deep Convolutional Neural Networks / Advances in Neural Information Processing Systems 60(6) : 1097~1105

[confproc] Langkilde-Geary, I / 2002 / An Empirical Verification of Coverage and Correctness for a General-purpose Sentence Generator / Proceedings of the 12th International Natural Language Generation Workshop : 17~24

[confproc] Nallapati, R. / 2016 / Abstractive Text Summarization using Sequence-to-sequence Rnns and Beyond / Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL) : 280~290

[web] Mairesse, F. / 2005 / Natural Language Generation: APT on Dialogue Models and Dialogue Systems / http://farm2.user.srcf.net/research/papers/ART-NLG.pdf

[confproc] Srivastava, R. K. / 2015 / Tranining Very Deep Networks / Advances in Neural Information Processing Systems : 2377~2385

[confproc] Sundermeyer, M. / 2012 / LSTM Neural Networks for Language Modeling / Thirteenth Annual Conference of the International Speech Communication Association

[confproc] Sutskever, I. / 2011 / Generating Text with Recurrent Neural Networks / Proceedings of the 28th International Conference on Machine Learning(ICML-11) : 1017~1024

[web] Wikipedia / 2017 / kowiki-latest-abstract.xml / https://dumps.wikimedia.org/kowiki/latest/

[web] Woodward, A. / 2016 / Market Share Analysis: Business Intelligence and Analytics Software / https://www.gartner.com/doc/3365832/market-share-analysis-business-intelligence

[confproc] Zheng, X. / 2013 / Deep Learning for Chinese Word Segmentation and POS Tagging / Conference on Empirical Methods in Natural Language Processing(EMNLP) : 647~657

[confproc] Zilly, J. G. / 2016 / Recurrent Highway Networks / Proceedings of the 34 th International Conference on Machine Learning

KJCKorea
Journal Central

Journal of the Korean Society for Library and Information Science 2023 KCI Impact Factor : 0.84

Research on the Utilization of Recurrent Neural Networks for Automatic Generation of Korean Definitional Sentences of Technical Terms

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of the Korean Society for Library and Information Science 2023 KCI Impact Factor : 0.84

Research on the Utilization of Recurrent Neural Networks for Automatic Generation of Korean Definitional Sentences of Technical Terms

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (1)

REFERENCES (22) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.