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

Cross-lingual natural language inference is a fundamental problem incross-lingual language understanding. Many recent works have used promptlearning to address the lack of annotated parallel corpora in XNLI. However,these methods adopt discrete prompting by simply translating the templates tothe target language and need external expert knowledge to design the templates.Besides, discrete prompts of human-designed template words are not trainablevectors and can not be migrated to target languages in the inference stageflexibly. In this paper, we propose a novel Soft prompt learning framework withthe Multilingual Verbalizer (SoftMV) for XNLI. SoftMV first constructscloze-style question with soft prompts for the input sample. Then we leveragebilingual dictionaries to generate an augmented multilingual question for theoriginal question. SoftMV adopts a multilingual verbalizer to align therepresentations of original and augmented multilingual questions into the samesemantic space with consistency regularization. Experimental results on XNLIdemonstrate that SoftMV can achieve state-of-the-art performance andsignificantly outperform the previous methods under the few-shot and full-shotcross-lingual transfer settings.

Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual Verbalizer