← Search

Chuanhao Lv

2 accepted papers

2023

Incorporating Probing Signals into Multimodal Machine Translation via Visual Question-Answering Pairs

EMNLP 2023long findings

This paper presents an in-depth study of multimodal machine translation (MMT), examining the prevailing understanding that MMT systems exhibit decreased sensitivity to visual information when text inputs are complete. Instead, we attribute this phenomenon to insufficient cross-modal interaction, rat…

Cited by 0SourcecodeScholar
2022

On Vision Features in Multimodal Machine Translation

ACL 2022long

Previous work on multimodal machine translation (MMT) has focused on the way of incorporating vision features into translation but little attention is on the quality of vision models. In this work, we investigate the impact of vision models on MMT. Given the fact that Transformer is becoming popular…