@inproceedings{chen-etal-2023-task,
title = "On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval",
author = "Chen, Jiayi and
Dai, Hanjun and
Dai, Bo and
Zhang, Aidong and
Wei, Wei",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.604",
doi = "10.18653/v1/2023.findings-emnlp.604",
pages = "9006--9025",
abstract = "Visually-rich document entity retrieval (VDER), which extracts key information (e.g. date, address) from document images like invoices and receipts, has become an important topic in industrial NLP applications. The emergence of new document types at a constant pace, each with its unique entity types, presents a unique challenge: many documents contain unseen entity types that occur only a couple of times. Addressing this challenge requires models to have the ability of learning entities in a few-shot manner. However, prior works for Few-shot VDER mainly address the problem at the document level with a predefined global entity space, which doesn{'}t account for the entity-level few-shot scenario: target entity types are locally personalized by each task and entity occurrences vary significantly among documents. To address this unexplored scenario, this paper studies a novel entity-level few-shot VDER task. The challenges lie in the uniqueness of the label space for each task and the increased complexity of out-of-distribution (OOD) contents. To tackle this novel task, we present a task-aware meta-learning based framework, with a central focus on achieving effective task personalization that distinguishes between in-task and out-of-task distribution. Specifically, we adopt a hierarchical decoder (HC) and employ contrastive learning (ContrastProtoNet) to achieve this goal. Furthermore, we introduce a new dataset, FewVEX, to boost future research in the field of entity-level few-shot VDER. Experimental results demonstrate our approaches significantly improve the robustness of popular meta-learning baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-task">
<titleInfo>
<title>On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiayi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanjun</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aidong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Visually-rich document entity retrieval (VDER), which extracts key information (e.g. date, address) from document images like invoices and receipts, has become an important topic in industrial NLP applications. The emergence of new document types at a constant pace, each with its unique entity types, presents a unique challenge: many documents contain unseen entity types that occur only a couple of times. Addressing this challenge requires models to have the ability of learning entities in a few-shot manner. However, prior works for Few-shot VDER mainly address the problem at the document level with a predefined global entity space, which doesn’t account for the entity-level few-shot scenario: target entity types are locally personalized by each task and entity occurrences vary significantly among documents. To address this unexplored scenario, this paper studies a novel entity-level few-shot VDER task. The challenges lie in the uniqueness of the label space for each task and the increased complexity of out-of-distribution (OOD) contents. To tackle this novel task, we present a task-aware meta-learning based framework, with a central focus on achieving effective task personalization that distinguishes between in-task and out-of-task distribution. Specifically, we adopt a hierarchical decoder (HC) and employ contrastive learning (ContrastProtoNet) to achieve this goal. Furthermore, we introduce a new dataset, FewVEX, to boost future research in the field of entity-level few-shot VDER. Experimental results demonstrate our approaches significantly improve the robustness of popular meta-learning baselines.</abstract>
<identifier type="citekey">chen-etal-2023-task</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.604</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.604</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>9006</start>
<end>9025</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval
%A Chen, Jiayi
%A Dai, Hanjun
%A Dai, Bo
%A Zhang, Aidong
%A Wei, Wei
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F chen-etal-2023-task
%X Visually-rich document entity retrieval (VDER), which extracts key information (e.g. date, address) from document images like invoices and receipts, has become an important topic in industrial NLP applications. The emergence of new document types at a constant pace, each with its unique entity types, presents a unique challenge: many documents contain unseen entity types that occur only a couple of times. Addressing this challenge requires models to have the ability of learning entities in a few-shot manner. However, prior works for Few-shot VDER mainly address the problem at the document level with a predefined global entity space, which doesn’t account for the entity-level few-shot scenario: target entity types are locally personalized by each task and entity occurrences vary significantly among documents. To address this unexplored scenario, this paper studies a novel entity-level few-shot VDER task. The challenges lie in the uniqueness of the label space for each task and the increased complexity of out-of-distribution (OOD) contents. To tackle this novel task, we present a task-aware meta-learning based framework, with a central focus on achieving effective task personalization that distinguishes between in-task and out-of-task distribution. Specifically, we adopt a hierarchical decoder (HC) and employ contrastive learning (ContrastProtoNet) to achieve this goal. Furthermore, we introduce a new dataset, FewVEX, to boost future research in the field of entity-level few-shot VDER. Experimental results demonstrate our approaches significantly improve the robustness of popular meta-learning baselines.
%R 10.18653/v1/2023.findings-emnlp.604
%U https://aclanthology.org/2023.findings-emnlp.604
%U https://doi.org/10.18653/v1/2023.findings-emnlp.604
%P 9006-9025
Markdown (Informal)
[On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval](https://aclanthology.org/2023.findings-emnlp.604) (Chen et al., Findings 2023)
ACL