| Presentation | 2023-11-28 Investigation of differences in latent variable space for different datasets in Sentence-BERT's image generation model Masato Izumi, Kenya Jin'no, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We have verified the degree to which sentence vectors, which are distributed representations of sentences generated by Sentence-BERT, capture the meaning of sentences using k-means and UMAP, and have confirmed that the sentence vectors generated by Sentence-BERT capture the meaning of sentences extremely well. We constructed a model for image generation using latent variables output by Sentence-BERT. By generating images from sentences, we have visualized the latent variables output from the natural language processing model. In this study, we investigated how the visualization of the latent variable space changes when the dataset of the image generation model is varied. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Sentence-BERT / representation learning / sentence vector / Latent Variable / Image generation |
| Paper # | NLP2023-61 |
| Date of Issue | 2023-11-21 (NLP) |
| Conference Information | |
| Committee | NLP |
|---|---|
| Conference Date | 2023/11/28(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Nago city commerce and industry association |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | NLP, etc. |
| Chair | Hiroyuki Torikai(Hosei Univ.) |
| Vice Chair | Yuichi Tanji(Kagawa Univ.) |
| Secretary | Yuichi Tanji(Gifu Univ.) |
| Assistant | Yoshikazu Yamanaka(Utsunomiya Univ.) / Eri Ioka(Shibaura Inst. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Nonlinear Problems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Investigation of differences in latent variable space for different datasets in Sentence-BERT's image generation model |
| Sub Title (in English) | |
| Keyword(1) | Sentence-BERT |
| Keyword(2) | representation learning |
| Keyword(3) | sentence vector |
| Keyword(4) | Latent Variable |
| Keyword(5) | Image generation |
| 1st Author's Name | Masato Izumi |
| 1st Author's Affiliation | Tokyo City University(Tokyo City Univ.) |
| 2nd Author's Name | Kenya Jin'no |
| 2nd Author's Affiliation | Tokyo City University(Tokyo City Univ.) |
| Date | 2023-11-28 |
| Paper # | NLP2023-61 |
| Volume (vol) | vol.123 |
| Number (no) | NLP-287 |
| Page | pp.pp.11-14(NLP), |
| #Pages | 4 |
| Date of Issue | 2023-11-21 (NLP) |