English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Visual context provides grounding information for multimodal machinetranslation (MMT). However, previous MMT models and probing studies on visualfeatures suggest that visual information is less explored in MMT as it is oftenredundant to textual information. In this paper, we propose an object-levelvisual context modeling framework (OVC) to efficiently capture and explorevisual information for multimodal machine translation. With detected objects,the proposed OVC encourages MMT to ground translation on desirable visualobjects by masking irrelevant objects in the visual modality. We equip theproposed with an additional object-masking loss to achieve this goal. Theobject-masking loss is estimated according to the similarity between maskedobjects and the source texts so as to encourage masking source-irrelevantobjects. Additionally, in order to generate vision-consistent target words, wefurther propose a vision-weighted translation loss for OVC. Experiments on MMTdatasets demonstrate that the proposed OVC model outperforms state-of-the-artMMT models and analyses show that masking irrelevant objects helps grounding inMMT.

Efficient Object-Level Visual Context Modeling for Multimodal Machine Translation: Masking Irrelevant Objects Helps Grounding