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

Recent work has shown that NLP tasks such as Relation Extraction (RE) can berecasted as Textual Entailment tasks using verbalizations, with strongperformance in zero-shot and few-shot settings thanks to pre-trained entailmentmodels. The fact that relations in current RE datasets are easily verbalizedcasts doubts on whether entailment would be effective in more complex tasks. Inthis work we show that entailment is also effective in Event ArgumentExtraction (EAE), reducing the need of manual annotation to 50% and 20% in ACEand WikiEvents respectively, while achieving the same performance as with fulltraining. More importantly, we show that recasting EAE as entailment alleviatesthe dependency on schemas, which has been a road-block for transferringannotations between domains. Thanks to the entailment, the multi-sourcetransfer between ACE and WikiEvents further reduces annotation down to 10% and5% (respectively) of the full training without transfer. Our analysis showsthat the key to good results is the use of several entailment datasets topre-train the entailment model. Similar to previous approaches, our methodrequires a small amount of effort for manual verbalization: only less than 15minutes per event argument type is needed, and comparable results can beachieved with users with different level of expertise.

Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning