no code implementations • 17 Aug 2022 • Emad Elwany, Allison Hegel, Marina Shah, Brendan Roof, Genevieve Peaslee, Quentin Rivet
Weak supervision has been applied to various Natural Language Understanding tasks in recent years.
no code implementations • 16 Jul 2021 • Allison Hegel, Marina Shah, Genevieve Peaslee, Brendan Roof, Emad Elwany
Large, pre-trained transformer models like BERT have achieved state-of-the-art results on document understanding tasks, but most implementations can only consider 512 tokens at a time.
no code implementations • NeurIPS Workshop Document_Intelligen 2019 • Emad Elwany, Dave Moore, Gaurav Oberoi
Fine-tuning language models, such as BERT, on domain specific corpora has proven to be valuable in domains like scientific papers and biomedical text.
no code implementations • 24 Mar 2017 • Justin Cranshaw, Emad Elwany, Todd Newman, Rafal Kocielnik, Bowen Yu, Sandeep Soni, Jaime Teevan, Andrés Monroy-Hernández
Although information workers may complain about meetings, they are an essential part of their work life.