@inproceedings{xu-etal-2023-sampling,
title = "Sampling Better Negatives for Distantly Supervised Named Entity Recognition",
author = "Xu, Lu and
Bing, Lidong and
Lu, Wei",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.300",
doi = "10.18653/v1/2023.findings-acl.300",
pages = "4874--4882",
abstract = "Distantly supervised named entity recognition (DS-NER) has been proposed to exploit the automatically labeled training data instead of human annotations. The distantly annotated datasets are often noisy and contain a considerable number of false negatives. The recent approach uses a weighted sampling approach to select a subset of negative samples for training. However, it requires a good classifier to assign weights to the negative samples. In this paper, we propose a simple and straightforward approach for selecting the top negative samples that have high similarities with all the positive samples for training. Our method achieves consistent performance improvements on four distantly supervised NER datasets. Our analysis also shows that it is critical to differentiate the true negatives from the false negatives.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2023-sampling">
<titleInfo>
<title>Sampling Better Negatives for Distantly Supervised Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Xu</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>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Lu</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>Findings of the Association for Computational Linguistics: ACL 2023</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>Distantly supervised named entity recognition (DS-NER) has been proposed to exploit the automatically labeled training data instead of human annotations. The distantly annotated datasets are often noisy and contain a considerable number of false negatives. The recent approach uses a weighted sampling approach to select a subset of negative samples for training. However, it requires a good classifier to assign weights to the negative samples. In this paper, we propose a simple and straightforward approach for selecting the top negative samples that have high similarities with all the positive samples for training. Our method achieves consistent performance improvements on four distantly supervised NER datasets. Our analysis also shows that it is critical to differentiate the true negatives from the false negatives.</abstract>
<identifier type="citekey">xu-etal-2023-sampling</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.300</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.300</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>4874</start>
<end>4882</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sampling Better Negatives for Distantly Supervised Named Entity Recognition
%A Xu, Lu
%A Bing, Lidong
%A Lu, Wei
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F xu-etal-2023-sampling
%X Distantly supervised named entity recognition (DS-NER) has been proposed to exploit the automatically labeled training data instead of human annotations. The distantly annotated datasets are often noisy and contain a considerable number of false negatives. The recent approach uses a weighted sampling approach to select a subset of negative samples for training. However, it requires a good classifier to assign weights to the negative samples. In this paper, we propose a simple and straightforward approach for selecting the top negative samples that have high similarities with all the positive samples for training. Our method achieves consistent performance improvements on four distantly supervised NER datasets. Our analysis also shows that it is critical to differentiate the true negatives from the false negatives.
%R 10.18653/v1/2023.findings-acl.300
%U https://aclanthology.org/2023.findings-acl.300
%U https://doi.org/10.18653/v1/2023.findings-acl.300
%P 4874-4882
Markdown (Informal)
[Sampling Better Negatives for Distantly Supervised Named Entity Recognition](https://aclanthology.org/2023.findings-acl.300) (Xu et al., Findings 2023)
ACL