Papers by Keisuke Shirai
Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows (2022.coling-1)
Copied to clipboard
Keisuke Shirai, Atsushi Hashimoto, Taichi Nishimura, Hirotaka Kameko, Shuhei Kurita, Yoshitaka Ushiku, Shinsuke Mori
| Challenge: | a new dataset enables us to learn a cooking action result for each object in a recipe text. |
| Approach: | They propose a multimodal dataset that enables us to learn a cooking action result for each object in a recipe text. |
| Outcome: | The proposed dataset reduces human annotation costs by allowing multimodal information retrieval. |
Image Description Dataset for Language Learners (2022.lrec-1)
Copied to clipboard
| Challenge: | Language learners are limited by the number of texts or speech they are asked to answer . automatic assessment of image descriptions requires a system that depends on both the learner's native language and the target language. |
| Approach: | They propose a dataset that consists of images, their descriptions, and assessment annotations . they propose 'automatic error correction' task that encodes multimodal information from a learner sentence with an image and accurately decodes a corrected sentence. |
| Outcome: | The proposed model can revise errors that cannot be revised without an image. |
Automatic Construction of a Large-Scale Corpus for Geoparsing Using Wikipedia Hyperlinks (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to evaluate geoparsing systems are small-scale and lack coverage of location expressions on general domains. |
| Approach: | They propose a method to construct a large-scale corpus for geoparsing from Wikipedia articles. |
| Outcome: | The proposed method can annotate multiple location expressions with coordinates even with ambiguous expressions. |