@inproceedings{voigt-etal-2024-plots,
title = "Plots Made Quickly: An Efficient Approach for Generating Visualizations from Natural Language Queries",
author = "Voigt, Henrik and
Lawonn, Kai and
Zarrie{\ss}, Sina",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1119",
pages = "12787--12793",
abstract = "Generating visualizations from natural language queries is a useful extension to visualization libraries such as Vega-Lite. The goal of the NL2VIS task is to generate a valid Vega-Lite specification from a data frame and a natural language query as input, which can then be rendered as a visualization. To enable real-time interaction with the data, small model sizes and fast inferences are required. Previous work has introduced custom neural network solutions with custom visualization specifications and has not systematically tested pre-trained LMs to solve this problem. In this work, we opt for a more generic approach that (i) evaluates pre-trained LMs of different sizes and (ii) uses string encodings of data frames and visualization specifications instead of custom specifications. In our experiments, we show that these representations, in combination with pre-trained LMs, scale better than current state-of-the-art models. In addition, the small and base versions of the T5 architecture achieve real-time interaction, while LLMs far exceed latency thresholds suitable for visual exploration tasks. In summary, our models generate visualization specifications in real-time on a CPU and establish a new state of the art on the NL2VIS benchmark nvBench.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="voigt-etal-2024-plots">
<titleInfo>
<title>Plots Made Quickly: An Efficient Approach for Generating Visualizations from Natural Language Queries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Henrik</namePart>
<namePart type="family">Voigt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Lawonn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generating visualizations from natural language queries is a useful extension to visualization libraries such as Vega-Lite. The goal of the NL2VIS task is to generate a valid Vega-Lite specification from a data frame and a natural language query as input, which can then be rendered as a visualization. To enable real-time interaction with the data, small model sizes and fast inferences are required. Previous work has introduced custom neural network solutions with custom visualization specifications and has not systematically tested pre-trained LMs to solve this problem. In this work, we opt for a more generic approach that (i) evaluates pre-trained LMs of different sizes and (ii) uses string encodings of data frames and visualization specifications instead of custom specifications. In our experiments, we show that these representations, in combination with pre-trained LMs, scale better than current state-of-the-art models. In addition, the small and base versions of the T5 architecture achieve real-time interaction, while LLMs far exceed latency thresholds suitable for visual exploration tasks. In summary, our models generate visualization specifications in real-time on a CPU and establish a new state of the art on the NL2VIS benchmark nvBench.</abstract>
<identifier type="citekey">voigt-etal-2024-plots</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1119</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12787</start>
<end>12793</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Plots Made Quickly: An Efficient Approach for Generating Visualizations from Natural Language Queries
%A Voigt, Henrik
%A Lawonn, Kai
%A Zarrieß, Sina
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F voigt-etal-2024-plots
%X Generating visualizations from natural language queries is a useful extension to visualization libraries such as Vega-Lite. The goal of the NL2VIS task is to generate a valid Vega-Lite specification from a data frame and a natural language query as input, which can then be rendered as a visualization. To enable real-time interaction with the data, small model sizes and fast inferences are required. Previous work has introduced custom neural network solutions with custom visualization specifications and has not systematically tested pre-trained LMs to solve this problem. In this work, we opt for a more generic approach that (i) evaluates pre-trained LMs of different sizes and (ii) uses string encodings of data frames and visualization specifications instead of custom specifications. In our experiments, we show that these representations, in combination with pre-trained LMs, scale better than current state-of-the-art models. In addition, the small and base versions of the T5 architecture achieve real-time interaction, while LLMs far exceed latency thresholds suitable for visual exploration tasks. In summary, our models generate visualization specifications in real-time on a CPU and establish a new state of the art on the NL2VIS benchmark nvBench.
%U https://aclanthology.org/2024.lrec-main.1119
%P 12787-12793
Markdown (Informal)
[Plots Made Quickly: An Efficient Approach for Generating Visualizations from Natural Language Queries](https://aclanthology.org/2024.lrec-main.1119) (Voigt et al., LREC-COLING 2024)
ACL