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

While pre-trained language models (PTLMs) have achieved noticeable success onmany NLP tasks, they still struggle for tasks that require event temporalreasoning, which is essential for event-centric applications. We present acontinual pre-training approach that equips PTLMs with targeted knowledge aboutevent temporal relations. We design self-supervised learning objectives torecover masked-out event and temporal indicators and to discriminate sentencesfrom their corrupted counterparts (where event or temporal indicators gotreplaced). By further pre-training a PTLM with these objectives jointly, wereinforce its attention to event and temporal information, yielding enhancedcapability on event temporal reasoning. This effective continual pre-trainingframework for event temporal reasoning (ECONET) improves the PTLMs' fine-tuningperformances across five relation extraction and question answering tasks andachieves new or on-par state-of-the-art performances in most of our downstreamtasks.

ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning