English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Pretrained Transformer based models finetuned on domain specific corpora havechanged the landscape of NLP. However, training or fine-tuning these models forindividual tasks can be time consuming and resource intensive. Thus, a lot ofcurrent research is focused on using transformers for multi-task learning(Raffel et al.,2020) and how to group the tasks to help a multi-task model tolearn effective representations that can be shared across tasks (Standley etal., 2020; Fifty et al., 2021). In this work, we show that a singlemulti-tasking model can match the performance of task specific models when thetask specific models show similar representations across all of their hiddenlayers and their gradients are aligned, i.e. their gradients follow the samedirection. We hypothesize that the above observations explain the effectivenessof multi-task learning. We validate our observations on our internalradiologist-annotated datasets on the cervical and lumbar spine. Our method issimple and intuitive, and can be used in a wide range of NLP problems.

Explaining the Effectiveness of Multi-Task Learning for Efficient Knowledge Extraction from Spine MRI Reports