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

Tongue twisters are meaningful sentences that are difficult to pronounce. Theprocess of automatically generating tongue twisters is challenging since thegenerated utterance must satisfy two conditions at once: phonetic difficultyand semantic meaning. Furthermore, phonetic difficulty is itself hard tocharacterize and is expressed in natural tongue twisters through aheterogeneous mix of phenomena such as alliteration and homophony. In thispaper, we propose PANCETTA: Phoneme Aware Neural Completion to Elicit TongueTwisters Automatically. We leverage phoneme representations to capture thenotion of phonetic difficulty, and we train language models to generateoriginal tongue twisters on two proposed task settings. To do this, we curate adataset called PANCETTA, consisting of existing English tongue twisters.Through automatic and human evaluation, as well as qualitative analysis, weshow that PANCETTA generates novel, phonetically difficult, fluent, andsemantically meaningful tongue twisters.

PANCETTA: Phoneme Aware Neural Completion to Elicit Tongue Twisters Automatically