@inproceedings{li-etal-2022-controllable,
title = "Controllable Dialogue Simulation with In-context Learning",
author = "Li, Zekun and
Chen, Wenhu and
Li, Shiyang and
Wang, Hong and
Qian, Jing and
Yan, Xifeng",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.318",
doi = "10.18653/v1/2022.findings-emnlp.318",
pages = "4330--4347",
abstract = "Building dialogue systems requires a large corpus of annotated dialogues. Such datasets are usually created via crowdsourcing, which is expensive and time-consuming. In this paper, we propose Dialogic, a novel dialogue simulation method based on large language model in-context learning to automate dataset creation. Seeded with a few annotated dialogues, Dialogic automatically selects in-context examples for demonstration and prompts GPT-3 to generate new dialogues and annotations in a controllable way. Our method can rapidly expand a small set of dialogue data with minimum or zero \textit{human involvement} and \textit{parameter update} and is thus much more cost-efficient and time-saving than crowdsourcing. Experimental results on the MultiWOZ dataset demonstrate that training a model on the simulated dialogues leads to even better performance than using the same amount of human-generated dialogues under the challenging low-resource settings, with as few as 85 dialogues as a seed. When the full training set is given, our method can still serve as an effective data augmentation method to further improve performance. Human evaluation results also show that our simulated dialogues have near-human fluency and annotation accuracy. The code and data are available at \textbf{ \url{https://github.com/Leezekun/dialogic}}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-controllable">
<titleInfo>
<title>Controllable Dialogue Simulation with In-context Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zekun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiyang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xifeng</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Building dialogue systems requires a large corpus of annotated dialogues. Such datasets are usually created via crowdsourcing, which is expensive and time-consuming. In this paper, we propose Dialogic, a novel dialogue simulation method based on large language model in-context learning to automate dataset creation. Seeded with a few annotated dialogues, Dialogic automatically selects in-context examples for demonstration and prompts GPT-3 to generate new dialogues and annotations in a controllable way. Our method can rapidly expand a small set of dialogue data with minimum or zero human involvement and parameter update and is thus much more cost-efficient and time-saving than crowdsourcing. Experimental results on the MultiWOZ dataset demonstrate that training a model on the simulated dialogues leads to even better performance than using the same amount of human-generated dialogues under the challenging low-resource settings, with as few as 85 dialogues as a seed. When the full training set is given, our method can still serve as an effective data augmentation method to further improve performance. Human evaluation results also show that our simulated dialogues have near-human fluency and annotation accuracy. The code and data are available at https://github.com/Leezekun/dialogic.</abstract>
<identifier type="citekey">li-etal-2022-controllable</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.318</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.318</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>4330</start>
<end>4347</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Controllable Dialogue Simulation with In-context Learning
%A Li, Zekun
%A Chen, Wenhu
%A Li, Shiyang
%A Wang, Hong
%A Qian, Jing
%A Yan, Xifeng
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F li-etal-2022-controllable
%X Building dialogue systems requires a large corpus of annotated dialogues. Such datasets are usually created via crowdsourcing, which is expensive and time-consuming. In this paper, we propose Dialogic, a novel dialogue simulation method based on large language model in-context learning to automate dataset creation. Seeded with a few annotated dialogues, Dialogic automatically selects in-context examples for demonstration and prompts GPT-3 to generate new dialogues and annotations in a controllable way. Our method can rapidly expand a small set of dialogue data with minimum or zero human involvement and parameter update and is thus much more cost-efficient and time-saving than crowdsourcing. Experimental results on the MultiWOZ dataset demonstrate that training a model on the simulated dialogues leads to even better performance than using the same amount of human-generated dialogues under the challenging low-resource settings, with as few as 85 dialogues as a seed. When the full training set is given, our method can still serve as an effective data augmentation method to further improve performance. Human evaluation results also show that our simulated dialogues have near-human fluency and annotation accuracy. The code and data are available at https://github.com/Leezekun/dialogic.
%R 10.18653/v1/2022.findings-emnlp.318
%U https://aclanthology.org/2022.findings-emnlp.318
%U https://doi.org/10.18653/v1/2022.findings-emnlp.318
%P 4330-4347
Markdown (Informal)
[Controllable Dialogue Simulation with In-context Learning](https://aclanthology.org/2022.findings-emnlp.318) (Li et al., Findings 2022)
ACL
- Zekun Li, Wenhu Chen, Shiyang Li, Hong Wang, Jing Qian, and Xifeng Yan. 2022. Controllable Dialogue Simulation with In-context Learning. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4330–4347, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.