@inproceedings{andrejczuk-etal-2022-table,
title = "Table-To-Text generation and pre-training with {T}ab{T}5",
author = "Andrejczuk, Ewa and
Eisenschlos, Julian and
Piccinno, Francesco and
Krichene, Syrine and
Altun, Yasemin",
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.503",
doi = "10.18653/v1/2022.findings-emnlp.503",
pages = "6758--6766",
abstract = "Encoder-only transformer models have been successfully applied to different table understanding tasks, as in TAPAS. A major limitation of these architectures is that they are constrained to classification-like tasks such as cell selection or entailment detection. We present TabT5, an encoder-decoder model that generates natural language text based on tables and textual inputs. TabT5 overcomes the encoder-only limitation by incorporating a decoder component and leverages the input structure with table specific embeddings and pre-training. TabT5 achieves new state-of-the-art results on several domains, including spreadsheet formula prediction with a 15{\%} increase in sequence accuracy, QA with a 2.5{\%} increase in sequence accuracy and data-to-text generation with a 2.5{\%} increase in BLEU.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="andrejczuk-etal-2022-table">
<titleInfo>
<title>Table-To-Text generation and pre-training with TabT5</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ewa</namePart>
<namePart type="family">Andrejczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julian</namePart>
<namePart type="family">Eisenschlos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Piccinno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syrine</namePart>
<namePart type="family">Krichene</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasemin</namePart>
<namePart type="family">Altun</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>Encoder-only transformer models have been successfully applied to different table understanding tasks, as in TAPAS. A major limitation of these architectures is that they are constrained to classification-like tasks such as cell selection or entailment detection. We present TabT5, an encoder-decoder model that generates natural language text based on tables and textual inputs. TabT5 overcomes the encoder-only limitation by incorporating a decoder component and leverages the input structure with table specific embeddings and pre-training. TabT5 achieves new state-of-the-art results on several domains, including spreadsheet formula prediction with a 15% increase in sequence accuracy, QA with a 2.5% increase in sequence accuracy and data-to-text generation with a 2.5% increase in BLEU.</abstract>
<identifier type="citekey">andrejczuk-etal-2022-table</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.503</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.503</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6758</start>
<end>6766</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Table-To-Text generation and pre-training with TabT5
%A Andrejczuk, Ewa
%A Eisenschlos, Julian
%A Piccinno, Francesco
%A Krichene, Syrine
%A Altun, Yasemin
%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 andrejczuk-etal-2022-table
%X Encoder-only transformer models have been successfully applied to different table understanding tasks, as in TAPAS. A major limitation of these architectures is that they are constrained to classification-like tasks such as cell selection or entailment detection. We present TabT5, an encoder-decoder model that generates natural language text based on tables and textual inputs. TabT5 overcomes the encoder-only limitation by incorporating a decoder component and leverages the input structure with table specific embeddings and pre-training. TabT5 achieves new state-of-the-art results on several domains, including spreadsheet formula prediction with a 15% increase in sequence accuracy, QA with a 2.5% increase in sequence accuracy and data-to-text generation with a 2.5% increase in BLEU.
%R 10.18653/v1/2022.findings-emnlp.503
%U https://aclanthology.org/2022.findings-emnlp.503
%U https://doi.org/10.18653/v1/2022.findings-emnlp.503
%P 6758-6766
Markdown (Informal)
[Table-To-Text generation and pre-training with TabT5](https://aclanthology.org/2022.findings-emnlp.503) (Andrejczuk et al., Findings 2022)
ACL
- Ewa Andrejczuk, Julian Eisenschlos, Francesco Piccinno, Syrine Krichene, and Yasemin Altun. 2022. Table-To-Text generation and pre-training with TabT5. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6758–6766, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.