05月26日(Fri) 09:30〜11:10 Q会場(ウインクあいち-8F 展示場)
| 演題番号 | 4Q1-4in2 |
|---|---|
| 題目 | Grounded noun/verb-phrases to images for RTE |
| 著者 | 韓 丹(AIRC/AIST) マルティネス パスクアル(Artificial Intelligence Research Center, AIST) |
| 時間 | 05月26日(Fri) 09:30〜11:10 |
| 概要 | We propose an algorithm to ground noun phrases and verb phrases to images, and deduce the relations between phrases from examining the similarity of two sets of images according to a simple similarity measure and a threshold. We evaluate our method in a textual entailment task. |
| 論文 | PDFファイル |