研究課題
In FY 2020, we mainly studied the following to improve multimodal neural machine translation (NNMT).1. MNMT with comparable sentences. We organized a shared task in the 8th Workshop on Asian Translation (WAT 2021) using the dataset we created in FY 2020. Our system achieved the best performance in this shared task.2. MNMT with semantic image regions and word-region alignment. We finalized our work MNMT with semantic image regions and word-region alignment and published them in two famous international journals of Neurocomputing and TASLP.3. Video-guided MT (VMT). We improved our VMT with a spatial hierarchical attention network as follows: We investigate and discuss spatial features; We research spatial feature filtering; We conduct experiments on the How2 dataset.
すべて 2022 2021 その他
すべて 国際共同研究 (1件) 雑誌論文 (3件) (うち査読あり 3件、 オープンアクセス 3件) 学会発表 (6件) (うち国際学会 4件) 備考 (1件)
Neurocomputing
巻: 476 ページ: 1～13
10.1016/j.neucom.2021.12.076
IEEE/ACM Transactions on Audio, Speech, and Language Processing
巻: 30 ページ: 244～259
10.1109/taslp.2021.3138719
Journal of Natural Language Processing
巻: 28 ページ: 1034～1052
10.5715/jnlp.28.1034
