@inproceedings{nguyen-etal-2024-docmaster,
title = "{DOCMASTER}: A Unified Platform for Annotation, Training, {\&} Inference in Document Question-Answering",
author = "Nguyen, Alex and
Wang, Zilong and
Shang, Jingbo and
Mekala, Dheeraj",
editor = "Chang, Kai-Wei and
Lee, Annie and
Rajani, Nazneen",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-demo.13",
pages = "128--136",
abstract = "The application of natural language processing models to PDF documents is pivotal for various business applications yet the challenge of training models for this purpose persists in businesses due to specific hurdles. These include the complexity of working with PDF formats that necessitate parsing text and layout information for curating training data and the lack of privacy-preserving annotation tools. This paper introduces DOCMASTER, a unified platform designed for annotating PDF documents, model training, and inference, tailored to document question-answering. The annotation interface enables users to input questions and highlight text spans within the PDF file as answers, saving layout information and text spans accordingly. Furthermore, DOCMASTER supports both state-of-the-art layout-aware and text models for comprehensive training purposes. Importantly, as annotations, training, and inference occur on-device, it also safeguards privacy. The platform has been instrumental in driving several research prototypes concerning document analysis such as the AI assistant utilized by University of California San Diego{'}s (UCSD) International Services and Engagement Office (ISEO) for processing a substantial volume of PDF documents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2024-docmaster">
<titleInfo>
<title>DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zilong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingbo</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dheeraj</namePart>
<namePart type="family">Mekala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annie</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nazneen</namePart>
<namePart type="family">Rajani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The application of natural language processing models to PDF documents is pivotal for various business applications yet the challenge of training models for this purpose persists in businesses due to specific hurdles. These include the complexity of working with PDF formats that necessitate parsing text and layout information for curating training data and the lack of privacy-preserving annotation tools. This paper introduces DOCMASTER, a unified platform designed for annotating PDF documents, model training, and inference, tailored to document question-answering. The annotation interface enables users to input questions and highlight text spans within the PDF file as answers, saving layout information and text spans accordingly. Furthermore, DOCMASTER supports both state-of-the-art layout-aware and text models for comprehensive training purposes. Importantly, as annotations, training, and inference occur on-device, it also safeguards privacy. The platform has been instrumental in driving several research prototypes concerning document analysis such as the AI assistant utilized by University of California San Diego’s (UCSD) International Services and Engagement Office (ISEO) for processing a substantial volume of PDF documents.</abstract>
<identifier type="citekey">nguyen-etal-2024-docmaster</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-demo.13</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>128</start>
<end>136</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering
%A Nguyen, Alex
%A Wang, Zilong
%A Shang, Jingbo
%A Mekala, Dheeraj
%Y Chang, Kai-Wei
%Y Lee, Annie
%Y Rajani, Nazneen
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F nguyen-etal-2024-docmaster
%X The application of natural language processing models to PDF documents is pivotal for various business applications yet the challenge of training models for this purpose persists in businesses due to specific hurdles. These include the complexity of working with PDF formats that necessitate parsing text and layout information for curating training data and the lack of privacy-preserving annotation tools. This paper introduces DOCMASTER, a unified platform designed for annotating PDF documents, model training, and inference, tailored to document question-answering. The annotation interface enables users to input questions and highlight text spans within the PDF file as answers, saving layout information and text spans accordingly. Furthermore, DOCMASTER supports both state-of-the-art layout-aware and text models for comprehensive training purposes. Importantly, as annotations, training, and inference occur on-device, it also safeguards privacy. The platform has been instrumental in driving several research prototypes concerning document analysis such as the AI assistant utilized by University of California San Diego’s (UCSD) International Services and Engagement Office (ISEO) for processing a substantial volume of PDF documents.
%U https://aclanthology.org/2024.naacl-demo.13
%P 128-136
Markdown (Informal)
[DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering](https://aclanthology.org/2024.naacl-demo.13) (Nguyen et al., NAACL 2024)
ACL