@inproceedings{nourbakhsh-etal-2024-towards,
title = "Towards a new research agenda for multimodal enterprise document understanding: What are we missing?",
author = "Nourbakhsh, Armineh and
Shah, Sameena and
Rose, Carolyn",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.870",
doi = "10.18653/v1/2024.findings-acl.870",
pages = "14610--14622",
abstract = "The field of multimodal document understanding has produced a suite of models that have achieved stellar performance across several tasks, even coming close to human performance on certain benchmarks. Nevertheless, the application of these models to real-world enterprise datasets remains constrained by a number of limitations. In this position paper, we discuss these limitations in the context of three key aspects of research: dataset curation, model development, and evaluation on downstream tasks. By analyzing 14 datasets and 7 SotA models, we identify major gaps in their utility in the context of a real-world scenario. We demonstrate how each limitation impedes the widespread use of SotA models in enterprise settings, and present a set of research challenges that are motivated by these limitations. Lastly, we propose a research agenda that is aimed at driving the field towards higher impact in enterprise applications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nourbakhsh-etal-2024-towards">
<titleInfo>
<title>Towards a new research agenda for multimodal enterprise document understanding: What are we missing?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Armineh</namePart>
<namePart type="family">Nourbakhsh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameena</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The field of multimodal document understanding has produced a suite of models that have achieved stellar performance across several tasks, even coming close to human performance on certain benchmarks. Nevertheless, the application of these models to real-world enterprise datasets remains constrained by a number of limitations. In this position paper, we discuss these limitations in the context of three key aspects of research: dataset curation, model development, and evaluation on downstream tasks. By analyzing 14 datasets and 7 SotA models, we identify major gaps in their utility in the context of a real-world scenario. We demonstrate how each limitation impedes the widespread use of SotA models in enterprise settings, and present a set of research challenges that are motivated by these limitations. Lastly, we propose a research agenda that is aimed at driving the field towards higher impact in enterprise applications.</abstract>
<identifier type="citekey">nourbakhsh-etal-2024-towards</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.870</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.870</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>14610</start>
<end>14622</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards a new research agenda for multimodal enterprise document understanding: What are we missing?
%A Nourbakhsh, Armineh
%A Shah, Sameena
%A Rose, Carolyn
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F nourbakhsh-etal-2024-towards
%X The field of multimodal document understanding has produced a suite of models that have achieved stellar performance across several tasks, even coming close to human performance on certain benchmarks. Nevertheless, the application of these models to real-world enterprise datasets remains constrained by a number of limitations. In this position paper, we discuss these limitations in the context of three key aspects of research: dataset curation, model development, and evaluation on downstream tasks. By analyzing 14 datasets and 7 SotA models, we identify major gaps in their utility in the context of a real-world scenario. We demonstrate how each limitation impedes the widespread use of SotA models in enterprise settings, and present a set of research challenges that are motivated by these limitations. Lastly, we propose a research agenda that is aimed at driving the field towards higher impact in enterprise applications.
%R 10.18653/v1/2024.findings-acl.870
%U https://aclanthology.org/2024.findings-acl.870
%U https://doi.org/10.18653/v1/2024.findings-acl.870
%P 14610-14622
Markdown (Informal)
[Towards a new research agenda for multimodal enterprise document understanding: What are we missing?](https://aclanthology.org/2024.findings-acl.870) (Nourbakhsh et al., Findings 2024)
ACL