21 citations · 44 across the 8 of their papers we have counts for
Showing cs.CLShow all
2 papers · 1 filter
cs.CL2023
Identifying Semantically Difficult Samples to Improve Text Classification
Shashank Mujumdar, Stuti Mehta, Hima Patel +1
In this paper, we investigate the effect of addressing difficult samples from a given text dataset on the downstream text classification task. We define difficult samples as being…
cs.CL2020★ 8 cited
Towards a Multi-modal, Multi-task Learning based Pre-training Framework for Document Representation Learning
Subhojeet Pramanik, Shashank Mujumdar, Hima Patel
Recent approaches in literature have exploited the multi-modal information in documents (text, layout, image) to serve specific downstream document tasks. However, they are limited…