Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation

Pre-trained language-vision models have shown remarkable performance on the visual question answering (VQA) task. However, most pre-trained models are trained by only considering monolingual learning, especially the resource-rich language like English. Training such models for multilingual setups de...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Khan, Humair Raj, Gupta, Deepak, Ekbal, Asif
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 10.09.2021
Subjects
Coders
Datasets
Distillation
English language
Language
Multilingualism
Questions
Teachers
Vision
Visual tasks
Online AccessGet full text

Cover

More Information
Summary:Pre-trained language-vision models have shown remarkable performance on the visual question answering (VQA) task. However, most pre-trained models are trained by only considering monolingual learning, especially the resource-rich language like English. Training such models for multilingual setups demand high computing resources and multilingual language-vision dataset which hinders their application in practice. To alleviate these challenges, we propose a knowledge distillation approach to extend an English language-vision model (teacher) into an equally effective multilingual and code-mixed model (student). Unlike the existing knowledge distillation methods, which only use the output from the last layer of the teacher network for distillation, our student model learns and imitates the teacher from multiple intermediate layers (language and vision encoders) with appropriately designed distillation objectives for incremental knowledge extraction. We also create the large-scale multilingual and code-mixed VQA dataset in eleven different language setups considering the multiple Indian and European languages. Experimental results and in-depth analysis show the effectiveness of the proposed VQA model over the pre-trained language-vision models on eleven diverse language setups.
ISSN:2331-8422