no code implementations • 14 Feb 2021 • Shaowei Yao, Jiwei Tan, Xi Chen, Keping Yang, Rong Xiao, Hongbo Deng, Xiaojun Wan
We propose a novel way to consider samples of different relevance confidence, and come up with a new training objective to learn a robust relevance model with desirable score distribution.
1 code implementation • ACL 2020 • Shaowei Yao, Xiaojun Wan
Multimodal Machine Translation (MMT) aims to introduce information from other modality, generally static images, to improve the translation quality.
Ranked #6 on Multimodal Machine Translation on Multi30K
no code implementations • ACL 2020 • Shaowei Yao, Tianming Wang, Xiaojun Wan
The graph-to-sequence (Graph2Seq) learning aims to transduce graph-structured representations to word sequences for text generation.