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

Identifying speakers of quotations in narratives is an important task inliterary analysis, with challenging scenarios including the out-of-domaininference for unseen speakers, and non-explicit cases where there are nospeaker mentions in surrounding context. In this work, we propose a simple andeffective approach SIG, a generation-based method that verbalizes the task andquotation input based on designed prompt templates, which also enables easyintegration of other auxiliary tasks that further bolster the speakeridentification performance. The prediction can either come from directgeneration by the model, or be determined by the highest generation probabilityof each speaker candidate. Based on our approach design, SIG supportsout-of-domain evaluation, and achieves open-world classification paradigm thatis able to accept any forms of candidate input. We perform both cross-domainevaluation and in-domain evaluation on PDNC, the largest dataset of this task,where empirical results suggest that SIG outperforms previous baselines ofcomplicated designs, as well as the zero-shot ChatGPT, especially excelling atthose hard non-explicit scenarios by up to 17% improvement. Additionalexperiments on another dataset WP further corroborate the efficacy of SIG.

SIG: Speaker Identification in Literature via Prompt-Based Generation