@inproceedings{xu-etal-2023-peerda,
title = "{P}eer{DA}: Data Augmentation via Modeling Peer Relation for Span Identification Tasks",
author = "Xu, Weiwen and
Li, Xin and
Deng, Yang and
Lam, Wai and
Bing, Lidong",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.484/",
doi = "10.18653/v1/2023.acl-long.484",
pages = "8681--8699",
abstract = "Span identification aims at identifying specific text spans from text input and classifying them into pre-defined categories. Different from previous works that merely leverage the Subordinate (SUB) relation (i.e. if a span is an instance of a certain category) to train models, this paper for the first time explores the Peer (PR) relation, which indicates that two spans are instances of the same category and share similar features. Specifically, a novel Peer Data Augmentation (PeerDA) approach is proposed which employs span pairs with the PR relation as the augmentation data for training. PeerDA has two unique advantages: (1) There are a large number of PR span pairs for augmenting the training data. (2) The augmented data can prevent the trained model from over-fitting the superficial span-category mapping by pushing the model to leverage the span semantics. Experimental results on ten datasets over four diverse tasks across seven domains demonstrate the effectiveness of PeerDA. Notably, PeerDA achieves state-of-the-art results on six of them."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2023-peerda">
<titleInfo>
<title>PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weiwen</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wai</namePart>
<namePart type="family">Lam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidong</namePart>
<namePart type="family">Bing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<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">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Span identification aims at identifying specific text spans from text input and classifying them into pre-defined categories. Different from previous works that merely leverage the Subordinate (SUB) relation (i.e. if a span is an instance of a certain category) to train models, this paper for the first time explores the Peer (PR) relation, which indicates that two spans are instances of the same category and share similar features. Specifically, a novel Peer Data Augmentation (PeerDA) approach is proposed which employs span pairs with the PR relation as the augmentation data for training. PeerDA has two unique advantages: (1) There are a large number of PR span pairs for augmenting the training data. (2) The augmented data can prevent the trained model from over-fitting the superficial span-category mapping by pushing the model to leverage the span semantics. Experimental results on ten datasets over four diverse tasks across seven domains demonstrate the effectiveness of PeerDA. Notably, PeerDA achieves state-of-the-art results on six of them.</abstract>
<identifier type="citekey">xu-etal-2023-peerda</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.484</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.484/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>8681</start>
<end>8699</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Tasks
%A Xu, Weiwen
%A Li, Xin
%A Deng, Yang
%A Lam, Wai
%A Bing, Lidong
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F xu-etal-2023-peerda
%X Span identification aims at identifying specific text spans from text input and classifying them into pre-defined categories. Different from previous works that merely leverage the Subordinate (SUB) relation (i.e. if a span is an instance of a certain category) to train models, this paper for the first time explores the Peer (PR) relation, which indicates that two spans are instances of the same category and share similar features. Specifically, a novel Peer Data Augmentation (PeerDA) approach is proposed which employs span pairs with the PR relation as the augmentation data for training. PeerDA has two unique advantages: (1) There are a large number of PR span pairs for augmenting the training data. (2) The augmented data can prevent the trained model from over-fitting the superficial span-category mapping by pushing the model to leverage the span semantics. Experimental results on ten datasets over four diverse tasks across seven domains demonstrate the effectiveness of PeerDA. Notably, PeerDA achieves state-of-the-art results on six of them.
%R 10.18653/v1/2023.acl-long.484
%U https://aclanthology.org/2023.acl-long.484/
%U https://doi.org/10.18653/v1/2023.acl-long.484
%P 8681-8699
Markdown (Informal)
[PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Tasks](https://aclanthology.org/2023.acl-long.484/) (Xu et al., ACL 2023)
ACL