| Presentation | 2018-12-07 Generation of Curriculum-Based Multiple Choice Questions Using Linked Data Tatsuki Fujii, Yuichi Sei, Yasuyuki Tahara, Akihiko Ohsuga, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Research on caption generation that modifies the contents of images and moving images with natural language using deep learning has gained considerable results and attracted attention in recent years. In this research, from the viewpoint of socially practical caption generation, a recipe for each cooking movie is generated for cooking movie data set of about 5 to 10 minutes acquired from YouTube called YouTube and annotated . As a proposed method, caption generation is performed by a model in which a vector of a sentence already generated in the same recipe is added to the input of an Encoder-Decoder, and comparison with an actually annotated recipe sentence is performed. We used Bleu for evaluation which is widely used for evaluation of image caption generation problem . |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Cooking Recipe / Deep Learning / Captioning / Contensity / Sentence Vector |
| Paper # | AI2018-32 |
| Date of Issue | 2018-11-30 (AI) |
| Conference Information | |
| Committee | AI |
|---|---|
| Conference Date | 2018/12/7(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Tsunenori Mine(Kyushu Univ.) |
| Vice Chair | Daisuke Katagami(Tokyo Polytechnic Univ.) / Naoki Fukuta(Shizuoka Univ.) |
| Secretary | Daisuke Katagami(Ritsumeikan Univ.) / Naoki Fukuta(Univ. of Electro-Comm.) |
| Assistant | Yuko Sakurai(AIST) |
| 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) | Generation of Curriculum-Based Multiple Choice Questions Using Linked Data |
| Sub Title (in English) | |
| Keyword(1) | Cooking Recipe |
| Keyword(2) | Deep Learning |
| Keyword(3) | Captioning |
| Keyword(4) | Contensity |
| Keyword(5) | Sentence Vector |
| 1st Author's Name | Tatsuki Fujii |
| 1st Author's Affiliation | University of Electro-Communications(UEC) |
| 2nd Author's Name | Yuichi Sei |
| 2nd Author's Affiliation | University of Electro-Communications(UEC) |
| 3rd Author's Name | Yasuyuki Tahara |
| 3rd Author's Affiliation | University of Electro-Communications(UEC) |
| 4th Author's Name | Akihiko Ohsuga |
| 4th Author's Affiliation | University of Electro-Communications(UEC) |
| Date | 2018-12-07 |
| Paper # | AI2018-32 |
| Volume (vol) | vol.118 |
| Number (no) | AI-350 |
| Page | pp.pp.37-41(AI), |
| #Pages | 5 |
| Date of Issue | 2018-11-30 (AI) |