Presentation | 2022-07-04 On Deep Paper Title Generation Considering Target Conferences Kento Kaku, Masato Kikuchi, Tadachika Ozono, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Paper title generation based on text summarization has been studied. However, unique and attractive title generation is not easy. This study develops a paper title generation method based on abstract summarization considering target conferences. We assume that if the linguistic characteristics of titles and abstracts of conference papers exist, we can use the differences to compose appropriate titles for target conference ranks. To investigate the differences, we introduced seven statistical metrics as linguistic characteristics. The metrics consist of the length and the different word counts of titles and abstracts and ROUGE-1, 2, 3, L, and BERTScore between titles and abstracts. As a result, we found slight trends in the characteristics by conference rank and authors' native language. However, we could not see significant differences among conference ranks to differentiate titles and abstracts for conference ranks. In other words, its characteristics could be used to evaluate the appropriateness of the title. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Paper Title Generation / Summarization Evaluation Metrics / ROUGE / BERTScore |
Paper # | AI2022-5 |
Date of Issue | 2022-06-27 (AI) |
Conference Information | |
Committee | AI |
---|---|
Conference Date | 2022/7/4(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Yuichi Sei(Univ. of Electro-Comm.) |
Vice Chair | Yuko Sakurai(AIST) / Tadachika Ozono(Nagoya Inst. of Tech.) |
Secretary | Yuko Sakurai(Tokyo Univ. of Agriculture and Technology) / Tadachika Ozono(Toho Univ.) |
Assistant | Kazutaka Matsuzaki(Chuo Univ.) |
Paper Information | |
Registration To | Technical Committee on Artificial Intelligence and Knowledge-Based Processing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | On Deep Paper Title Generation Considering Target Conferences |
Sub Title (in English) | |
Keyword(1) | Paper Title Generation |
Keyword(2) | Summarization Evaluation Metrics |
Keyword(3) | ROUGE |
Keyword(4) | BERTScore |
1st Author's Name | Kento Kaku |
1st Author's Affiliation | Nagoya Institute of Technology(NIT) |
2nd Author's Name | Masato Kikuchi |
2nd Author's Affiliation | Nagoya Institute of Technology(NIT) |
3rd Author's Name | Tadachika Ozono |
3rd Author's Affiliation | Nagoya Institute of Technology(NIT) |
Date | 2022-07-04 |
Paper # | AI2022-5 |
Volume (vol) | vol.122 |
Number (no) | AI-94 |
Page | pp.pp.25-30(AI), |
#Pages | 6 |
Date of Issue | 2022-06-27 (AI) |