@inproceedings{kowieski-etal-2024-tapasgo-transfer,
title = "{TAPASGO}: Transfer Learning towards a {G}erman-Language Tabular Question Answering Model",
author = "Kowieski, Dominik Andreas and
Hellwig, Michael and
Feilhauer, Thomas",
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.1354",
pages = "15579--15584",
abstract = "Processing tabular data holds significant importance across various domains and applications. This study investigates the performance and limitations of fine-tuned models for tabular data analysis, specifically focusing on using fine-tuning mechanics on an English model towards a potential German model. The validation of the effectiveness of the transfer learning approach compares the performance of the fine-tuned German model and of the original English model on test data from the German training set. A potential shortcut that translates the German test data into English serves for comparison. Results reveal that the fine-tuned model outperforms the original model significantly, demonstrating the effectiveness of transfer learning even for a limited amount of training data. One also observes that the English model can effectively process translated German tabular data, albeit with a slight accuracy drop compared to fine-tuning. The model evaluation extends to real-world data extracted from the sustainability reports of a financial institution. The fine-tuned model proves superior in extracting knowledge from these training-unrelated tables, indicating its potential applicability in practical scenarios. This paper also releases the first manually annotated dataset for German Table Question Answering and the related annotation tool.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kowieski-etal-2024-tapasgo-transfer">
<titleInfo>
<title>TAPASGO: Transfer Learning towards a German-Language Tabular Question Answering Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="given">Andreas</namePart>
<namePart type="family">Kowieski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Hellwig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Feilhauer</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>Processing tabular data holds significant importance across various domains and applications. This study investigates the performance and limitations of fine-tuned models for tabular data analysis, specifically focusing on using fine-tuning mechanics on an English model towards a potential German model. The validation of the effectiveness of the transfer learning approach compares the performance of the fine-tuned German model and of the original English model on test data from the German training set. A potential shortcut that translates the German test data into English serves for comparison. Results reveal that the fine-tuned model outperforms the original model significantly, demonstrating the effectiveness of transfer learning even for a limited amount of training data. One also observes that the English model can effectively process translated German tabular data, albeit with a slight accuracy drop compared to fine-tuning. The model evaluation extends to real-world data extracted from the sustainability reports of a financial institution. The fine-tuned model proves superior in extracting knowledge from these training-unrelated tables, indicating its potential applicability in practical scenarios. This paper also releases the first manually annotated dataset for German Table Question Answering and the related annotation tool.</abstract>
<identifier type="citekey">kowieski-etal-2024-tapasgo-transfer</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1354</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>15579</start>
<end>15584</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TAPASGO: Transfer Learning towards a German-Language Tabular Question Answering Model
%A Kowieski, Dominik Andreas
%A Hellwig, Michael
%A Feilhauer, Thomas
%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 kowieski-etal-2024-tapasgo-transfer
%X Processing tabular data holds significant importance across various domains and applications. This study investigates the performance and limitations of fine-tuned models for tabular data analysis, specifically focusing on using fine-tuning mechanics on an English model towards a potential German model. The validation of the effectiveness of the transfer learning approach compares the performance of the fine-tuned German model and of the original English model on test data from the German training set. A potential shortcut that translates the German test data into English serves for comparison. Results reveal that the fine-tuned model outperforms the original model significantly, demonstrating the effectiveness of transfer learning even for a limited amount of training data. One also observes that the English model can effectively process translated German tabular data, albeit with a slight accuracy drop compared to fine-tuning. The model evaluation extends to real-world data extracted from the sustainability reports of a financial institution. The fine-tuned model proves superior in extracting knowledge from these training-unrelated tables, indicating its potential applicability in practical scenarios. This paper also releases the first manually annotated dataset for German Table Question Answering and the related annotation tool.
%U https://aclanthology.org/2024.lrec-main.1354
%P 15579-15584
Markdown (Informal)
[TAPASGO: Transfer Learning towards a German-Language Tabular Question Answering Model](https://aclanthology.org/2024.lrec-main.1354) (Kowieski et al., LREC-COLING 2024)
ACL