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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Cross-task knowledge transfer via multi-task learning has recently maderemarkable progress in general NLP tasks. However, entity tracking on theprocedural text has not benefited from such knowledge transfer because of itsdistinct formulation, i.e., tracking the event flow while following structuralconstraints. State-of-the-art entity tracking approaches either designcomplicated model architectures or rely on task-specific pre-training toachieve good results. To this end, we propose MeeT, a Multi-tasklearning-enabled entity Tracking approach, which utilizes knowledge gained fromgeneral domain tasks to improve entity tracking. Specifically, MeeT firstfine-tunes T5, a pre-trained multi-task learning model, with entitytracking-specialized QA formats, and then employs our customized decodingstrategy to satisfy the structural constraints. MeeT achieves state-of-the-artperformances on two popular entity tracking datasets, even though it does notrequire any task-specific architecture design or pre-training.

Entity Tracking via Effective Use of Multi-Task Learning Model and Mention-guided Decoding