TY  - CONF
AU  - Adarsh Tiwari
AU  - Sanket Biswas
AU  - Josep Llados
A2  - ICDAR
PY  - 2023//
TI  - Can Pre-trained Language Models Help in Understanding Handwritten Symbols?
BT  - 17th International Conference on Document Analysis and Recognition
SP  - 199–211
VL  - 14193
N2  - The emergence of transformer models like BERT, GPT-2, GPT-3, RoBERTa, T5 for natural language understanding tasks has opened the floodgates towards solving a wide array of machine learning tasks in other modalities like images, audio, music, sketches and so on. These language models are domain-agnostic and as a result could be applied to 1-D sequences of any kind. However, the key challenge lies in bridging the modality gap so that they could generate strong features beneficial for out-of-domain tasks. This work focuses on leveraging the power of such pre-trained language models and discusses the challenges in predicting challenging handwritten symbols and alphabets.
UR  - https://link.springer.com/chapter/10.1007/978-3-031-41498-5_15
N1  - DAG
ID  - Adarsh Tiwari2023
ER  -