@inproceedings{bojic-etal-2023-data,
title = "A Data-centric Framework for Improving Domain-specific Machine Reading Comprehension Datasets",
author = "Bojic, Iva and
Halim, Josef and
Suharman, Verena and
Tar, Sreeja and
Ong, Qi Chwen and
Phung, Duy and
Ravaut, Mathieu and
Joty, Shafiq and
Car, Josip",
editor = "Tafreshi, Shabnam and
Akula, Arjun and
Sedoc, Jo{\~a}o and
Drozd, Aleksandr and
Rogers, Anna and
Rumshisky, Anna",
booktitle = "Proceedings of the Fourth Workshop on Insights from Negative Results in NLP",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.insights-1.3",
doi = "10.18653/v1/2023.insights-1.3",
pages = "19--32",
abstract = "Low-quality data can cause downstream problems in high-stakes applications. Data-centric approach emphasizes on improving dataset quality to enhance model performance. High-quality datasets are needed for general-purpose Large Language Models (LLMs) training, as well as for domain-specific models, which are usually small in size as it is costly to engage a large number of domain experts for their creation. Thus, it is vital to ensure high-quality domain-specific training data. In this paper, we propose a framework for enhancing the data quality of original datasets. (Code and dataset are available at https://github.com/IvaBojic/framework). We applied the proposed framework to four biomedical datasets and showed relative improvement of up to 33{\%}/40{\%} for fine-tuning of retrieval/reader models on the BioASQ dataset when using back translation to enhance the original dataset quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bojic-etal-2023-data">
<titleInfo>
<title>A Data-centric Framework for Improving Domain-specific Machine Reading Comprehension Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iva</namePart>
<namePart type="family">Bojic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Halim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verena</namePart>
<namePart type="family">Suharman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sreeja</namePart>
<namePart type="family">Tar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="given">Chwen</namePart>
<namePart type="family">Ong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duy</namePart>
<namePart type="family">Phung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Ravaut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josip</namePart>
<namePart type="family">Car</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Insights from Negative Results in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Akula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandr</namePart>
<namePart type="family">Drozd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Low-quality data can cause downstream problems in high-stakes applications. Data-centric approach emphasizes on improving dataset quality to enhance model performance. High-quality datasets are needed for general-purpose Large Language Models (LLMs) training, as well as for domain-specific models, which are usually small in size as it is costly to engage a large number of domain experts for their creation. Thus, it is vital to ensure high-quality domain-specific training data. In this paper, we propose a framework for enhancing the data quality of original datasets. (Code and dataset are available at https://github.com/IvaBojic/framework). We applied the proposed framework to four biomedical datasets and showed relative improvement of up to 33%/40% for fine-tuning of retrieval/reader models on the BioASQ dataset when using back translation to enhance the original dataset quality.</abstract>
<identifier type="citekey">bojic-etal-2023-data</identifier>
<identifier type="doi">10.18653/v1/2023.insights-1.3</identifier>
<location>
<url>https://aclanthology.org/2023.insights-1.3</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>19</start>
<end>32</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Data-centric Framework for Improving Domain-specific Machine Reading Comprehension Datasets
%A Bojic, Iva
%A Halim, Josef
%A Suharman, Verena
%A Tar, Sreeja
%A Ong, Qi Chwen
%A Phung, Duy
%A Ravaut, Mathieu
%A Joty, Shafiq
%A Car, Josip
%Y Tafreshi, Shabnam
%Y Akula, Arjun
%Y Sedoc, João
%Y Drozd, Aleksandr
%Y Rogers, Anna
%Y Rumshisky, Anna
%S Proceedings of the Fourth Workshop on Insights from Negative Results in NLP
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F bojic-etal-2023-data
%X Low-quality data can cause downstream problems in high-stakes applications. Data-centric approach emphasizes on improving dataset quality to enhance model performance. High-quality datasets are needed for general-purpose Large Language Models (LLMs) training, as well as for domain-specific models, which are usually small in size as it is costly to engage a large number of domain experts for their creation. Thus, it is vital to ensure high-quality domain-specific training data. In this paper, we propose a framework for enhancing the data quality of original datasets. (Code and dataset are available at https://github.com/IvaBojic/framework). We applied the proposed framework to four biomedical datasets and showed relative improvement of up to 33%/40% for fine-tuning of retrieval/reader models on the BioASQ dataset when using back translation to enhance the original dataset quality.
%R 10.18653/v1/2023.insights-1.3
%U https://aclanthology.org/2023.insights-1.3
%U https://doi.org/10.18653/v1/2023.insights-1.3
%P 19-32
Markdown (Informal)
[A Data-centric Framework for Improving Domain-specific Machine Reading Comprehension Datasets](https://aclanthology.org/2023.insights-1.3) (Bojic et al., insights-WS 2023)
ACL
- Iva Bojic, Josef Halim, Verena Suharman, Sreeja Tar, Qi Chwen Ong, Duy Phung, Mathieu Ravaut, Shafiq Joty, and Josip Car. 2023. A Data-centric Framework for Improving Domain-specific Machine Reading Comprehension Datasets. In Proceedings of the Fourth Workshop on Insights from Negative Results in NLP, pages 19–32, Dubrovnik, Croatia. Association for Computational Linguistics.