Presentation 2023-09-07
An Investigation of Suggested Keywords Generation Method for Search Behavior Analysis Using Large-Scale Language Model
Yumeto Inaoka, Mitsuo Yoshida,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In content marketing, it is vital to produce beneficial content that fits with customer needs by utilizing the knowledge available in search engines. This paper focuses on suggested keywords and investigate a method for generating these keywords using a large-scale language model. The model was fine-tuned and evaluated using suggested keywords obtained from search engines. Automatic evaluation results showed that the generated suggested keywords had low similarity with the test data. In the manual evaluation, it was confirmed that approximately 70% of the outputs have equal or higher utility for search behavior analysis compared to search engines. It demonstrates the effectiveness of the approach.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Large-Scale Language Model / Keyword Suggestion / Autocomplete / Search Behavior Analysis
Paper # NLC2023-9
Date of Issue 2023-08-30 (NLC)

Conference Information
Committee NLC
Conference Date 2023/9/6(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Osaka Metropolitan University. Nakamozu Campus.
Topics (in Japanese) (See Japanese page)
Topics (in English) The 20th Text Analytics Symposium
Chair Mitsuo Yoshida(Univ. of Tsukuba)
Vice Chair Hiroki Sakaji(Univ. of Tokyo) / Takeshi Kobayakawa(NHK)
Secretary Hiroki Sakaji(rinna) / Takeshi Kobayakawa(Hiroshima Univ. of Economics)
Assistant Kanjin Takahashi(Sansan) / Yasuhiro Ogawa(Nagoya Univ.)

Paper Information
Registration To Technical Committee on Natural Language Understanding and Models of Communication
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An Investigation of Suggested Keywords Generation Method for Search Behavior Analysis Using Large-Scale Language Model
Sub Title (in English)
Keyword(1) Large-Scale Language Model
Keyword(2) Keyword Suggestion
Keyword(3) Autocomplete
Keyword(4) Search Behavior Analysis
1st Author's Name Yumeto Inaoka
1st Author's Affiliation Faber Company Inc.(Faber Company)
2nd Author's Name Mitsuo Yoshida
2nd Author's Affiliation University of Tsukuba(Univ. Tsukuba)
Date 2023-09-07
Paper # NLC2023-9
Volume (vol) vol.123
Number (no) NLC-176
Page pp.pp.47-50(NLC),
#Pages 4
Date of Issue 2023-08-30 (NLC)