@inproceedings{gehrmann-etal-2023-tata,
title = "{T}a{TA}: A Multilingual Table-to-Text Dataset for {A}frican Languages",
author = "Gehrmann, Sebastian and
Ruder, Sebastian and
Nikolaev, Vitaly and
Botha, Jan and
Chavinda, Michael and
Parikh, Ankur and
Rivera, Clara",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.118",
doi = "10.18653/v1/2023.findings-emnlp.118",
pages = "1719--1740",
abstract = "Existing data-to-text generation datasets are mostly limited to English. To address this lack of data, we create Table-to-Text in African languages (TaTA), the first large multilingual table-to-text dataset with a focus on African languages. We created TaTA by transcribing figures and accompanying text in bilingual reports by the Demographic and Health Surveys Program, followed by professional translation to make the dataset fully parallel. TaTA includes 8,700 examples in nine languages including four African languages (Hausa, Igbo, Swahili, and Yor{\`u}b{\'a}) and a zero-shot test language (Russian). We additionally release screenshots of the original figures for future research on multilingual multi-modal approaches. Through an in-depth human evaluation, we show that TaTA is challenging for current models and that less than half the outputs from an mT5-XXL-based model are understandable and attributable to the source data. Our results highlight a) the need for validating metrics; and b) the importance of domain-specific metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gehrmann-etal-2023-tata">
<titleInfo>
<title>TaTA: A Multilingual Table-to-Text Dataset for African Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vitaly</namePart>
<namePart type="family">Nikolaev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Botha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Chavinda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ankur</namePart>
<namePart type="family">Parikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clara</namePart>
<namePart type="family">Rivera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing data-to-text generation datasets are mostly limited to English. To address this lack of data, we create Table-to-Text in African languages (TaTA), the first large multilingual table-to-text dataset with a focus on African languages. We created TaTA by transcribing figures and accompanying text in bilingual reports by the Demographic and Health Surveys Program, followed by professional translation to make the dataset fully parallel. TaTA includes 8,700 examples in nine languages including four African languages (Hausa, Igbo, Swahili, and Yorùbá) and a zero-shot test language (Russian). We additionally release screenshots of the original figures for future research on multilingual multi-modal approaches. Through an in-depth human evaluation, we show that TaTA is challenging for current models and that less than half the outputs from an mT5-XXL-based model are understandable and attributable to the source data. Our results highlight a) the need for validating metrics; and b) the importance of domain-specific metrics.</abstract>
<identifier type="citekey">gehrmann-etal-2023-tata</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.118</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.118</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>1719</start>
<end>1740</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TaTA: A Multilingual Table-to-Text Dataset for African Languages
%A Gehrmann, Sebastian
%A Ruder, Sebastian
%A Nikolaev, Vitaly
%A Botha, Jan
%A Chavinda, Michael
%A Parikh, Ankur
%A Rivera, Clara
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F gehrmann-etal-2023-tata
%X Existing data-to-text generation datasets are mostly limited to English. To address this lack of data, we create Table-to-Text in African languages (TaTA), the first large multilingual table-to-text dataset with a focus on African languages. We created TaTA by transcribing figures and accompanying text in bilingual reports by the Demographic and Health Surveys Program, followed by professional translation to make the dataset fully parallel. TaTA includes 8,700 examples in nine languages including four African languages (Hausa, Igbo, Swahili, and Yorùbá) and a zero-shot test language (Russian). We additionally release screenshots of the original figures for future research on multilingual multi-modal approaches. Through an in-depth human evaluation, we show that TaTA is challenging for current models and that less than half the outputs from an mT5-XXL-based model are understandable and attributable to the source data. Our results highlight a) the need for validating metrics; and b) the importance of domain-specific metrics.
%R 10.18653/v1/2023.findings-emnlp.118
%U https://aclanthology.org/2023.findings-emnlp.118
%U https://doi.org/10.18653/v1/2023.findings-emnlp.118
%P 1719-1740
Markdown (Informal)
[TaTA: A Multilingual Table-to-Text Dataset for African Languages](https://aclanthology.org/2023.findings-emnlp.118) (Gehrmann et al., Findings 2023)
ACL
- Sebastian Gehrmann, Sebastian Ruder, Vitaly Nikolaev, Jan Botha, Michael Chavinda, Ankur Parikh, and Clara Rivera. 2023. TaTA: A Multilingual Table-to-Text Dataset for African Languages. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1719–1740, Singapore. Association for Computational Linguistics.