PT Unknown
AU Josep Brugues Pujolras
   Lluis Gomez
   Dimosthenis Karatzas
TI A Multilingual Approach to Scene Text Visual Question Answering
BT Document Analysis Systems.15th IAPR International Workshop, (DAS2022)
PY 2022
BP 65
EP 79
DI 10.1007/978-3-031-06555-2_5
DE Scene text; Visual question answering; Multilingual word embeddings; Vision and language; Deep learning
AB Scene Text Visual Question Answering (ST-VQA) has recently emerged as a hot research topic in Computer Vision. Current ST-VQA models have a big potential for many types of applications but lack the ability to perform well on more than one language at a time due to the lack of multilingual data, as well as the use of monolingual word embeddings for training. In this work, we explore the possibility to obtain bilingual and multilingual VQA models. In that regard, we use an already established VQA model that uses monolingual word embeddings as part of its pipeline and substitute them by FastText and BPEmb multilingual word embeddings that have been aligned to English. Our experiments demonstrate that it is possible to obtain bilingual and multilingual VQA models with a minimal loss in performance in languages not used during training, as well as a multilingual model trained in multiple languages that match the performance of the respective monolingual baselines.
ER