Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

docs: updated article reference in Multi-Task docs page #1668

Merged
merged 9 commits into from
Dec 3, 2023
Merged

docs: updated article reference in Multi-Task docs page #1668

Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
1a59449
Release 1.0.0
IgnatovFedor Nov 8, 2022
49e74be
Release 1.0.1
IgnatovFedor Nov 22, 2022
a1e9477
Release 1.0.2
IgnatovFedor Jan 10, 2023
8d8bdaf
Release 1.1.0
IgnatovFedor Feb 17, 2023
0448c73
Release 1.1.1
IgnatovFedor Mar 14, 2023
d39944b
Release 1.2.0
IgnatovFedor Jun 6, 2023
34d240c
Release 1.3.0
IgnatovFedor Aug 17, 2023
168e979
Release 1.4.0
IgnatovFedor Oct 17, 2023
97ba401
correct reference
dimakarp1996 Nov 1, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion docs/features/models/multitask_bert.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,8 @@ Multi-task BERT in DeepPavlov
=============================

Multi-task BERT in DeepPavlov is an implementation of BERT training algorithm published in the paper
`Multi-Task Deep Neural Networks for Natural Language Understanding <https://arxiv.org/abs/1901.11504>`_.
`Knowledge Transfer Between Tasks and Languages in the Multi-task
Encoder-agnostic Transformer-based Models <https://www.dialog-21.ru/media/5902/karpovdpluskonovalovv002.pdf>`_.

The idea is to share BERT body between several tasks. This is necessary if a model pipe has several
components using BERT and the amount of GPU memory is limited. Each task has its own 'head' part attached to the
Expand Down