Download PDFOpen PDF in browser

Automatic extractive summarization for Japanese documents by LDA

12 pagesPublished: September 20, 2022

Abstract

The demand for automatic summarization of newspaper headlines and article sum- maries has increasing with various studies on automatic summarization being currently conducted. However, there are only a few studies on Japanese documents as compared English documents.
In this paper, wheter existing summarization methods can be effective for academic pa- pers written in Japanese is verified. First, we demonstrate the effectiveness of topic-based extractive summarization methods Latent Semantic Analysis (LSA). Then, a more effec- tive topic-based extractive summarization is possible by using Latent Dirichlet Allocation (LDA) is demonstrated.

Keyphrases: automatic summarization, extractive summarization, lda, lsa, natural language processing

In: Tokuro Matsuo (editor). Proceedings of 11th International Congress on Advanced Applied Informatics, vol 81, pages 41-52.

BibTeX entry
@inproceedings{IIAIAAI2021-Winter:Automatic_extractive_summarization_Japanese,
  author    = {Hideyuki Sawahata and Tetsuro Nishino},
  title     = {Automatic extractive summarization for Japanese documents by LDA},
  booktitle = {Proceedings of 11th International Congress on Advanced Applied Informatics},
  editor    = {Tokuro Matsuo},
  series    = {EPiC Series in Computing},
  volume    = {81},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {/publications/paper/Drms},
  doi       = {10.29007/p5cf},
  pages     = {41-52},
  year      = {2022}}
Download PDFOpen PDF in browser