@inproceedings{li-etal-2023-language,
title = "Can Language Models Make Fun? A Case Study in {C}hinese Comical Crosstalk",
author = "Li, Jianquan and
Wu, XiangBo and
Liu, Xiaokang and
Xie, Qianqian and
Tiwari, Prayag and
Wang, Benyou",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.419",
doi = "10.18653/v1/2023.acl-long.419",
pages = "7581--7596",
abstract = "Language is the principal tool for human communication, in which humor is one of the most attractive parts. Producing natural language like humans using computers, a.k.a, Natural Language Generation (NLG), has been widely used for dialogue systems, chatbots, machine translation, as well as computer-aid creation e.g., idea generations, scriptwriting. However, the humor aspect of natural language is relatively under-investigated, especially in the age of pre-trained language models. In this work, we aim to preliminarily test *whether NLG can generate humor as humans do*. We build a largest dataset consisting of numerous **C**hinese **C**omical **C**rosstalk scripts (called **C**3 in short), which is for a popular Chinese performing art called {`}Xiangsheng{'} or {`}相声{'} since 1800s.We benchmark various generation approaches including training-from-scratch Seq2seq, fine-tuned middle-scale PLMs, and large-scale PLMs (with and without fine-tuning). Moreover, we also conduct a human assessment, showing that 1) *large-scale pretraining largely improves crosstalk generation quality*; and 2) *even the scripts generated from the best PLM is far from what we expect*. We conclude humor generation could be largely improved using large-scaled PLMs, but it is still in its infancy. The data and benchmarking code are publicly available in [\url{https://github.com/anonNo2/crosstalk-generation}](\url{https://github.com/anonNo2/crosstalk-generation}).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-language">
<titleInfo>
<title>Can Language Models Make Fun? A Case Study in Chinese Comical Crosstalk</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianquan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">XiangBo</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaokang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianqian</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prayag</namePart>
<namePart type="family">Tiwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benyou</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language is the principal tool for human communication, in which humor is one of the most attractive parts. Producing natural language like humans using computers, a.k.a, Natural Language Generation (NLG), has been widely used for dialogue systems, chatbots, machine translation, as well as computer-aid creation e.g., idea generations, scriptwriting. However, the humor aspect of natural language is relatively under-investigated, especially in the age of pre-trained language models. In this work, we aim to preliminarily test *whether NLG can generate humor as humans do*. We build a largest dataset consisting of numerous **C**hinese **C**omical **C**rosstalk scripts (called **C**3 in short), which is for a popular Chinese performing art called ‘Xiangsheng’ or ‘相声’ since 1800s.We benchmark various generation approaches including training-from-scratch Seq2seq, fine-tuned middle-scale PLMs, and large-scale PLMs (with and without fine-tuning). Moreover, we also conduct a human assessment, showing that 1) *large-scale pretraining largely improves crosstalk generation quality*; and 2) *even the scripts generated from the best PLM is far from what we expect*. We conclude humor generation could be largely improved using large-scaled PLMs, but it is still in its infancy. The data and benchmarking code are publicly available in [https://github.com/anonNo2/crosstalk-generation](https://github.com/anonNo2/crosstalk-generation).</abstract>
<identifier type="citekey">li-etal-2023-language</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.419</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.419</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>7581</start>
<end>7596</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Language Models Make Fun? A Case Study in Chinese Comical Crosstalk
%A Li, Jianquan
%A Wu, XiangBo
%A Liu, Xiaokang
%A Xie, Qianqian
%A Tiwari, Prayag
%A Wang, Benyou
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F li-etal-2023-language
%X Language is the principal tool for human communication, in which humor is one of the most attractive parts. Producing natural language like humans using computers, a.k.a, Natural Language Generation (NLG), has been widely used for dialogue systems, chatbots, machine translation, as well as computer-aid creation e.g., idea generations, scriptwriting. However, the humor aspect of natural language is relatively under-investigated, especially in the age of pre-trained language models. In this work, we aim to preliminarily test *whether NLG can generate humor as humans do*. We build a largest dataset consisting of numerous **C**hinese **C**omical **C**rosstalk scripts (called **C**3 in short), which is for a popular Chinese performing art called ‘Xiangsheng’ or ‘相声’ since 1800s.We benchmark various generation approaches including training-from-scratch Seq2seq, fine-tuned middle-scale PLMs, and large-scale PLMs (with and without fine-tuning). Moreover, we also conduct a human assessment, showing that 1) *large-scale pretraining largely improves crosstalk generation quality*; and 2) *even the scripts generated from the best PLM is far from what we expect*. We conclude humor generation could be largely improved using large-scaled PLMs, but it is still in its infancy. The data and benchmarking code are publicly available in [https://github.com/anonNo2/crosstalk-generation](https://github.com/anonNo2/crosstalk-generation).
%R 10.18653/v1/2023.acl-long.419
%U https://aclanthology.org/2023.acl-long.419
%U https://doi.org/10.18653/v1/2023.acl-long.419
%P 7581-7596
Markdown (Informal)
[Can Language Models Make Fun? A Case Study in Chinese Comical Crosstalk](https://aclanthology.org/2023.acl-long.419) (Li et al., ACL 2023)
ACL
- Jianquan Li, XiangBo Wu, Xiaokang Liu, Qianqian Xie, Prayag Tiwari, and Benyou Wang. 2023. Can Language Models Make Fun? A Case Study in Chinese Comical Crosstalk. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7581–7596, Toronto, Canada. Association for Computational Linguistics.
