@inproceedings{li-etal-2023-set,
title = "Set Learning for Generative Information Extraction",
author = "Li, Jiangnan and
Zhang, Yice and
Liang, Bin and
Wong, Kam-Fai and
Xu, Ruifeng",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.806",
doi = "10.18653/v1/2023.emnlp-main.806",
pages = "13043--13052",
abstract = "Recent efforts have endeavored to employ the sequence-to-sequence (Seq2Seq) model in Information Extraction (IE) due to its potential to tackle multiple IE tasks in a unified manner. Under this formalization, multiple structured objects are concatenated as the target sequence in a predefined order. However, structured objects, by their nature, constitute an unordered set. Consequently, this formalization introduces a potential order bias, which can impair model learning. Targeting this issue, this paper proposes a set learning approach that considers multiple permutations of structured objects to optimize set probability approximately. Notably, our approach does not require any modifications to model structures, making it easily integrated into existing generative IE frameworks. Experiments show that our method consistently improves existing frameworks on vast tasks and datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-set">
<titleInfo>
<title>Set Learning for Generative Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiangnan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yice</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kam-Fai</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</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>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</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>Recent efforts have endeavored to employ the sequence-to-sequence (Seq2Seq) model in Information Extraction (IE) due to its potential to tackle multiple IE tasks in a unified manner. Under this formalization, multiple structured objects are concatenated as the target sequence in a predefined order. However, structured objects, by their nature, constitute an unordered set. Consequently, this formalization introduces a potential order bias, which can impair model learning. Targeting this issue, this paper proposes a set learning approach that considers multiple permutations of structured objects to optimize set probability approximately. Notably, our approach does not require any modifications to model structures, making it easily integrated into existing generative IE frameworks. Experiments show that our method consistently improves existing frameworks on vast tasks and datasets.</abstract>
<identifier type="citekey">li-etal-2023-set</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.806</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.806</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>13043</start>
<end>13052</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Set Learning for Generative Information Extraction
%A Li, Jiangnan
%A Zhang, Yice
%A Liang, Bin
%A Wong, Kam-Fai
%A Xu, Ruifeng
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F li-etal-2023-set
%X Recent efforts have endeavored to employ the sequence-to-sequence (Seq2Seq) model in Information Extraction (IE) due to its potential to tackle multiple IE tasks in a unified manner. Under this formalization, multiple structured objects are concatenated as the target sequence in a predefined order. However, structured objects, by their nature, constitute an unordered set. Consequently, this formalization introduces a potential order bias, which can impair model learning. Targeting this issue, this paper proposes a set learning approach that considers multiple permutations of structured objects to optimize set probability approximately. Notably, our approach does not require any modifications to model structures, making it easily integrated into existing generative IE frameworks. Experiments show that our method consistently improves existing frameworks on vast tasks and datasets.
%R 10.18653/v1/2023.emnlp-main.806
%U https://aclanthology.org/2023.emnlp-main.806
%U https://doi.org/10.18653/v1/2023.emnlp-main.806
%P 13043-13052
Markdown (Informal)
[Set Learning for Generative Information Extraction](https://aclanthology.org/2023.emnlp-main.806) (Li et al., EMNLP 2023)
ACL
- Jiangnan Li, Yice Zhang, Bin Liang, Kam-Fai Wong, and Ruifeng Xu. 2023. Set Learning for Generative Information Extraction. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13043–13052, Singapore. Association for Computational Linguistics.