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

Event Coreference Resolution (ECR) is the task of linking mentions of thesame event either within or across documents. Most mention pairs are notcoreferent, yet many that are coreferent can be identified through simpletechniques such as lemma matching of the event triggers or the sentences inwhich they appear. Existing methods for training coreference systems samplefrom a largely skewed distribution, making it difficult for the algorithm tolearn coreference beyond surface matching. Additionally, these methods areintractable because of the quadratic operations needed. To address thesechallenges, we break the problem of ECR into two parts: a) a heuristic toefficiently filter out a large number of non-coreferent pairs, and b) atraining approach on a balanced set of coreferent and non-coreferent mentionpairs. By following this approach, we show that we get comparable results tothe state of the art on two popular ECR datasets while significantly reducingcompute requirements. We also analyze the mention pairs that are "hard" toaccurately classify as coreferent or non-coreferent. Code athttps://github.com/ahmeshaf/lemma_ce_coref

$2 * n$ is better than $n^2$: Decomposing Event Coreference Resolution into Two Tractable Problems