TMT: A Transformer-Based Modal Translator for Improving Multimodal Sequence Representations in Audio Visual Scene-Aware Dialog

Wubo Li, Dongwei Jiang, Wei Zou, Xiangang Li
2020 Interspeech 2020  
Audio Visual Scene-aware Dialog (AVSD) is a task to generate responses when discussing about a given video. The previous state-of-the-art model shows superior performance for this task using Transformer-based architecture. However, there remain some limitations in learning better representation of modalities. Inspired by Neural Machine Translation (NMT), we propose the Transformer-based Modal Translator (TMT) to learn the representations of the source modal sequence by translating the source
more » ... al sequence to the related target modal sequence in a supervised manner. Based on Multimodal Transformer Networks (MTN), we apply TMT to video and dialog, proposing MTN-TMT for the video-grounded dialog system. On the AVSD track of the Dialog System Technology Challenge 7, MTN-TMT outperforms the MTN and other submission models in both Video and Text task and Text Only task. Compared with MTN, MTN-TMT improves all metrics, especially, achieving relative improvement up to 14.1% on CIDEr.
doi:10.21437/interspeech.2020-2359 dblp:conf/interspeech/LiJZL20 fatcat:o7yntqz3obe5bagebmirdhoyrm