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

Language is the principal tool for human communication, in which humor is oneof the most attractive parts. Producing natural language like humans usingcomputers, a.k.a, Natural Language Generation (NLG), has been widely used fordialogue systems, chatbots, machine translation, as well as computer-aidcreation e.g., idea generations, scriptwriting. However, the humor aspect ofnatural language is relatively under-investigated, especially in the age ofpre-trained language models. In this work, we aim to preliminarily test whetherNLG can generate humor as humans do. We build a new dataset consisting ofnumerous digitized Chinese Comical Crosstalk scripts (called C$^3$ in short),which is for a popular Chinese performing art called `Xiangsheng' since 1800s.(For convenience for non-Chinese speakers, we called `crosstalk' for`Xiangsheng' in this paper.) We benchmark various generation approachesincluding training-from-scratch Seq2seq, fine-tuned middle-scale PLMs, andlarge-scale PLMs (with and without fine-tuning). Moreover, we also conduct ahuman assessment, showing that 1) large-scale pretraining largely improvescrosstalk generation quality; and 2) even the scripts generated from the bestPLM is far from what we expect, with only 65% quality of human-createdcrosstalk. We conclude, humor generation could be largely improved usinglarge-scaled PLMs, but it is still in its infancy.  The data and benchmarking code is publicly available in\url{https://github.com/anonNo2/crosstalk-generation}.

Can Language Models Make Fun? A Case Study in Chinese Comical Crosstalk