@inproceedings{liu-etal-2022-artist,
title = "{ARTIST}: A Transformer-based {C}hinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledge",
author = "Liu, Tingting and
Wang, Chengyu and
Zhu, Xiangru and
Li, Lei and
Qiu, Minghui and
Huang, Jun and
Gao, Ming and
Xiao, Yanghua",
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.62/",
doi = "10.18653/v1/2022.findings-emnlp.62",
pages = "881--888",
abstract = "Text-to-Image Synthesis (TIS) is a popular task to convert natural language texts into realistic images. Recently, transformer-based TIS models (such as DALL-E) have been proposed using the encoder-decoder architectures. Yet, these billion-scale TIS models are difficult to tune and deploy in resource-constrained environments. In addition, there is a lack of language-specific TIS benchmarks for Chinese, together with high-performing models with moderate sizes. In this work, we present ARTIST, A tRansformer-based Chinese Text-to-Image SynThesizer for high-resolution image generation. In ARTIST, the rich linguistic and relational knowledge facts are injected into the model to ensure better model performance without the usage of ultra-large models. We further establish a large-scale Chinese TIS benchmark with the re-production results of state-of-the-art transformer-based TIS models.Results show ARTIST outperforms previous approaches."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2022-artist">
<titleInfo>
<title>ARTIST: A Transformer-based Chinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tingting</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangru</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghui</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanghua</namePart>
<namePart type="family">Xiao</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>Text-to-Image Synthesis (TIS) is a popular task to convert natural language texts into realistic images. Recently, transformer-based TIS models (such as DALL-E) have been proposed using the encoder-decoder architectures. Yet, these billion-scale TIS models are difficult to tune and deploy in resource-constrained environments. In addition, there is a lack of language-specific TIS benchmarks for Chinese, together with high-performing models with moderate sizes. In this work, we present ARTIST, A tRansformer-based Chinese Text-to-Image SynThesizer for high-resolution image generation. In ARTIST, the rich linguistic and relational knowledge facts are injected into the model to ensure better model performance without the usage of ultra-large models. We further establish a large-scale Chinese TIS benchmark with the re-production results of state-of-the-art transformer-based TIS models.Results show ARTIST outperforms previous approaches.</abstract>
<identifier type="citekey">liu-etal-2022-artist</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.62</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.62/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>881</start>
<end>888</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ARTIST: A Transformer-based Chinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledge
%A Liu, Tingting
%A Wang, Chengyu
%A Zhu, Xiangru
%A Li, Lei
%A Qiu, Minghui
%A Huang, Jun
%A Gao, Ming
%A Xiao, Yanghua
%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 liu-etal-2022-artist
%X Text-to-Image Synthesis (TIS) is a popular task to convert natural language texts into realistic images. Recently, transformer-based TIS models (such as DALL-E) have been proposed using the encoder-decoder architectures. Yet, these billion-scale TIS models are difficult to tune and deploy in resource-constrained environments. In addition, there is a lack of language-specific TIS benchmarks for Chinese, together with high-performing models with moderate sizes. In this work, we present ARTIST, A tRansformer-based Chinese Text-to-Image SynThesizer for high-resolution image generation. In ARTIST, the rich linguistic and relational knowledge facts are injected into the model to ensure better model performance without the usage of ultra-large models. We further establish a large-scale Chinese TIS benchmark with the re-production results of state-of-the-art transformer-based TIS models.Results show ARTIST outperforms previous approaches.
%R 10.18653/v1/2022.findings-emnlp.62
%U https://aclanthology.org/2022.findings-emnlp.62/
%U https://doi.org/10.18653/v1/2022.findings-emnlp.62
%P 881-888
Markdown (Informal)
[ARTIST: A Transformer-based Chinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledge](https://aclanthology.org/2022.findings-emnlp.62/) (Liu et al., Findings 2022)
ACL
- Tingting Liu, Chengyu Wang, Xiangru Zhu, Lei Li, Minghui Qiu, Jun Huang, Ming Gao, and Yanghua Xiao. 2022. ARTIST: A Transformer-based Chinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledge. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 881–888, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.