@inproceedings{tang-etal-2022-textbox,
title = "{T}ext{B}ox 2.0: A Text Generation Library with Pre-trained Language Models",
author = "Tang, Tianyi and
Li, Junyi and
Chen, Zhipeng and
Hu, Yiwen and
Yu, Zhuohao and
Dai, Wenxun and
Zhao, Wayne Xin and
Nie, Jian-yun and
Wen, Ji-rong",
editor = "Che, Wanxiang and
Shutova, Ekaterina",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-demos.42/",
doi = "10.18653/v1/2022.emnlp-demos.42",
pages = "435--444",
abstract = "To facilitate research on text generation, this paper presents a comprehensive and unified library, TextBox 2.0, focusing on the use of pre-trained language models (PLMs). To be comprehensive, our library covers 13 common text generation tasks and their corresponding 83 datasets and further incorporates 45 PLMs covering general, translation, Chinese, dialogue, controllable, distilled, prompting, and lightweight PLMs. We also implement 4 efficient training strategies and provide 4 generation objectives for pre-training new PLMs from scratch. To be unified, we design the interfaces to support the entire research pipeline (from data loading to training and evaluation), ensuring that each step can be fulfilled in a unified way. Despite the rich functionality, it is easy to use our library, either through the friendly Python API or command line. To validate the effectiveness of our library, we conduct extensive experiments and exemplify four types of research scenarios. The project is released at the link: \url{https://github.com/RUCAIBox/TextBox#2.0}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2022-textbox">
<titleInfo>
<title>TextBox 2.0: A Text Generation Library with Pre-trained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhipeng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiwen</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuohao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenxun</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wayne</namePart>
<namePart type="given">Xin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian-yun</namePart>
<namePart type="family">Nie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji-rong</namePart>
<namePart type="family">Wen</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>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To facilitate research on text generation, this paper presents a comprehensive and unified library, TextBox 2.0, focusing on the use of pre-trained language models (PLMs). To be comprehensive, our library covers 13 common text generation tasks and their corresponding 83 datasets and further incorporates 45 PLMs covering general, translation, Chinese, dialogue, controllable, distilled, prompting, and lightweight PLMs. We also implement 4 efficient training strategies and provide 4 generation objectives for pre-training new PLMs from scratch. To be unified, we design the interfaces to support the entire research pipeline (from data loading to training and evaluation), ensuring that each step can be fulfilled in a unified way. Despite the rich functionality, it is easy to use our library, either through the friendly Python API or command line. To validate the effectiveness of our library, we conduct extensive experiments and exemplify four types of research scenarios. The project is released at the link: https://github.com/RUCAIBox/TextBox#2.0.</abstract>
<identifier type="citekey">tang-etal-2022-textbox</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-demos.42</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-demos.42/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>435</start>
<end>444</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TextBox 2.0: A Text Generation Library with Pre-trained Language Models
%A Tang, Tianyi
%A Li, Junyi
%A Chen, Zhipeng
%A Hu, Yiwen
%A Yu, Zhuohao
%A Dai, Wenxun
%A Zhao, Wayne Xin
%A Nie, Jian-yun
%A Wen, Ji-rong
%Y Che, Wanxiang
%Y Shutova, Ekaterina
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F tang-etal-2022-textbox
%X To facilitate research on text generation, this paper presents a comprehensive and unified library, TextBox 2.0, focusing on the use of pre-trained language models (PLMs). To be comprehensive, our library covers 13 common text generation tasks and their corresponding 83 datasets and further incorporates 45 PLMs covering general, translation, Chinese, dialogue, controllable, distilled, prompting, and lightweight PLMs. We also implement 4 efficient training strategies and provide 4 generation objectives for pre-training new PLMs from scratch. To be unified, we design the interfaces to support the entire research pipeline (from data loading to training and evaluation), ensuring that each step can be fulfilled in a unified way. Despite the rich functionality, it is easy to use our library, either through the friendly Python API or command line. To validate the effectiveness of our library, we conduct extensive experiments and exemplify four types of research scenarios. The project is released at the link: https://github.com/RUCAIBox/TextBox#2.0.
%R 10.18653/v1/2022.emnlp-demos.42
%U https://aclanthology.org/2022.emnlp-demos.42/
%U https://doi.org/10.18653/v1/2022.emnlp-demos.42
%P 435-444
Markdown (Informal)
[TextBox 2.0: A Text Generation Library with Pre-trained Language Models](https://aclanthology.org/2022.emnlp-demos.42/) (Tang et al., EMNLP 2022)
ACL
- Tianyi Tang, Junyi Li, Zhipeng Chen, Yiwen Hu, Zhuohao Yu, Wenxun Dai, Wayne Xin Zhao, Jian-yun Nie, and Ji-rong Wen. 2022. TextBox 2.0: A Text Generation Library with Pre-trained Language Models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 435–444, Abu Dhabi, UAE. Association for Computational Linguistics.