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

Frame Semantic Role Labeling (FSRL) identifies arguments and labels them withframe semantic roles defined in FrameNet. Previous researches tend to divideFSRL into argument identification and role classification. Such methods usuallymodel role classification as naive multi-class classification and treatarguments individually, which neglects label semantics and interactions betweenarguments and thus hindering performance and generalization of models. In thispaper, we propose a query-based framework named ArGument Extractor withDefinitions in FrameNet (AGED) to mitigate these problems. Definitions offrames and frame elements (FEs) in FrameNet can be used to query arguments intext. Encoding text-definition pairs can guide models in learning labelsemantics and strengthening argument interactions. Experiments show that AGEDoutperforms previous state-of-the-art by up to 1.3 F1-score in two FrameNetdatasets and the generalization power of AGED in zero-shot and fewshotscenarios. Our code and technical appendix is available athttps://github.com/PKUnlp-icler/AGED.

Query Your Model with Definitions in FrameNet: An Effective Method for Frame Semantic Role Labeling