Visual Question Answering Dataset for Bilingual Image Understanding: A Study of Cross-Lingual Transfer Using Attention Maps
Nobuyuki Shimizu, Na Rong(Tokyo Tech), Takashi Miyazaki
The 27th International Conference on Computational Linguistics (COLING 2018), 2018/8
自然言語処理 (Natural Language Processing) 画像処理 (Image Processing) クラウドソーシング (Crowdsourcing)
- Visual question answering (VQA) is a challenging task that requires a computer system to under- stand both a question and an image. While there is much research on VQA in English, there is a lack of datasets for other languages, and English annotation is not directly applicable in those languages. To deal with this, we have created a Japanese VQA dataset by using crowdsourced annotation with images from the Visual Genome dataset. This is the first such dataset in Japanese. As another contribution, we propose a cross-lingual method for making use of English annotation to improve a Japanese VQA system. The proposed method is based on a popular VQA method that uses an attention mechanism. We use attention maps generated from English questions to help improve the Japanese VQA task. The proposed method experimentally performed better than simply using a monolingual corpus, which demonstrates the effectiveness of using attention maps to transfer cross-lingual information.
Visual Question Answering Dataset for Bilingual Image Understanding: A Study of Cross-Lingual Transfer Using Attention Maps（外部サイト／External Site Link）