DOI QR코드

DOI QR Code

딥러닝을 이용한 기형도 시의 핵심 이미지 분석

Deep Learning Application for Core Image Analysis of the Poems by Ki Hyung-Do

  • 고광호 (평택대 스마트자동차학과)
  • 투고 : 2021.08.02
  • 심사 : 2021.08.09
  • 발행 : 2021.08.31

초록

전후방 단어들의 인접 여부 혹은 후방 단어들의 순서를 학습할 수 있는 통계 기법인 SVD, 딥러닝 기법인 CBOW, LSTM으로 단어벡터를 구할 수 있다. 이렇게 학습된 단어벡터를 기형도의 시에 적용하여 핵심 이미지를 대표하는 단어들과 유사도 높은 단어를 구해서 분석해 보았다. 시적 이미지와 어울리지 않는 단어들이 연산되기도 하지만 그 단어가 사용된 시적 맥락에서는 기준 단어와 유사한 이미지를 표현하고 있음을 알 수 있었다. 이러한 단어벡터를 활용하면 핵심 이미지를 대표하는 단어들의 관계와 유사한 관계의 다른 단어들도 유추할 수 있다. 따라서 통계 기법인 SVD 및 딥러닝 기법인 CBOW와 LSTM으로 구한 단어벡터의 유사도 및 유추 연산을 통해 대상 시를 다양하고 심도 깊게 분석할 수 있다.

It's possible to get the word-vector by the statistical SVD or deep-learning CBOW and LSTM methods and theses ones learn the contexts of forward/backward words or the sequence of following words. It's used to analyze the poems by Ki Hyung-do with similar words recommended by the word-vector showing the core images of the poetry. It seems at first sight that the words don't go well with the images but they express the similar style described by the reference words once you look close the contexts of the specific poems. The word-vector can analogize the words having the same relations with the ones between the representative words for the core images of the poems. Therefore you can analyze the poems in depth and in variety with the similarity and analogy operations by the word-vector estimated with the statistical SVD or deep-learning CBOW and LSTM methods.

키워드

참고문헌

  1. Hyungsuc Kang, Janghoon Yang, "Analyzing Semantic Relations of Word Vectors trained by The Word2vec Model", Journal of KIISE, 46(10), pp. 1088-1093, 2019, DOI : 10.5626/JOK.2019.46.10.1088
  2. Heimerl, F., Gleicher, M., "Interactive Analysis of Word Vector Embeddings", Computer Graphics Forum, 37(3), pp. 253-265, 2018, DOI : 10.1111/cgf.13417
  3. Song, Ji-seon, "A Study on the Topophobia of Stuck 'Empty Place' in Modernity of Ki Hyungdo's Poetry", The Korean Language and Literature, vol. 89, pp. 177-207, 2021.
  4. Basirat, A. Nivre, "Real-valued Syntactic Word Vectors", Journal of Experimental & Theoretical Artificial Intelligence, 32(4), pp. 557-579, 2020, DOI : 10.1080/0952813X.2019.1653385
  5. Kim Hyeun, "Experiencing an Empty Room Closed Forever", 「Black Leaf in the mouth」, Moonji Publishing, pp. 135, 1989.
  6. Lee Sekyung, "Space Consciousness of the Road Expressed in the Poems by Ki Hyungdo", Korean Culture Technology, 3(0), pp. 73-86 2007.
  7. Lee Seungchoel, "Cognitive Meanings Study on Fog of Hyeong-do Ki", Korean Language & Literature, 59(0), pp. 255-280, 2015.
  8. Shin Jinsuk, "The Book/Cinema of the Refused World - Studies in 「Black Leaf in the Mouth」 by Ki Hyungdo", Cross-Culture Studies, 7(0), pp. 187-208, 2004.
  9. Kwon Hyeockwoong, "The Subject in Gi, Hyoung-do's poems", Journal of Korean Literary Criticism, 34(0), pp. 65-87, 2011.
  10. Lee Jongwon, "A Study on the Method of Reading Poetry Using the Concept of Descriptive Genre", Korean Literature Education Research, 51(0), pp. 177-208, 2016. https://doi.org/10.37192/KLER.51.6
  11. Park Jeonghye, "A Study on the Simsang-Poetry Therapy Utilizing Gi Hyeong Do's Poetry", Journal of Arts Psychotherapy, 9(3), pp. 39-66, 2013.
  12. Oh Hyungyup, "An Inquiry of Walter Benjamins Literary Art Theory Laying stress on irony and allegory", Literary Criticism, 33, pp. 295-320, 2009.