@inproceedings{daza-etal-2022-slotgan,
title = "{S}lot{GAN}: Detecting Mentions in Text via Adversarial Distant Learning",
author = "Daza, Daniel and
Cochez, Michael and
Groth, Paul",
editor = "Vlachos, Andreas and
Agrawal, Priyanka and
Martins, Andr{\'e} and
Lampouras, Gerasimos and
Lyu, Chunchuan",
booktitle = "Proceedings of the Sixth Workshop on Structured Prediction for NLP",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.spnlp-1.4",
doi = "10.18653/v1/2022.spnlp-1.4",
pages = "32--39",
abstract = "We present SlotGAN, a framework for training a mention detection model that only requires unlabeled text and a gazetteer. It consists of a generator trained to extract spans from an input sentence, and a discriminator trained to determine whether a span comes from the generator, or from the gazetteer. We evaluate the method on English newswire data and compare it against supervised, weakly-supervised, and unsupervised methods. We find that the performance of the method is lower than these baselines, because it tends to generate more and longer spans, and in some cases it relies only on capitalization. In other cases, it generates spans that are valid but differ from the benchmark. When evaluated with metrics based on overlap, we find that SlotGAN performs within 95{\%} of the precision of a supervised method, and 84{\%} of its recall. Our results suggest that the model can generate spans that overlap well, but an additional filtering mechanism is required.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="daza-etal-2022-slotgan">
<titleInfo>
<title>SlotGAN: Detecting Mentions in Text via Adversarial Distant Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Daza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Cochez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Groth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Structured Prediction for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyanka</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Lampouras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunchuan</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present SlotGAN, a framework for training a mention detection model that only requires unlabeled text and a gazetteer. It consists of a generator trained to extract spans from an input sentence, and a discriminator trained to determine whether a span comes from the generator, or from the gazetteer. We evaluate the method on English newswire data and compare it against supervised, weakly-supervised, and unsupervised methods. We find that the performance of the method is lower than these baselines, because it tends to generate more and longer spans, and in some cases it relies only on capitalization. In other cases, it generates spans that are valid but differ from the benchmark. When evaluated with metrics based on overlap, we find that SlotGAN performs within 95% of the precision of a supervised method, and 84% of its recall. Our results suggest that the model can generate spans that overlap well, but an additional filtering mechanism is required.</abstract>
<identifier type="citekey">daza-etal-2022-slotgan</identifier>
<identifier type="doi">10.18653/v1/2022.spnlp-1.4</identifier>
<location>
<url>https://aclanthology.org/2022.spnlp-1.4</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>32</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SlotGAN: Detecting Mentions in Text via Adversarial Distant Learning
%A Daza, Daniel
%A Cochez, Michael
%A Groth, Paul
%Y Vlachos, Andreas
%Y Agrawal, Priyanka
%Y Martins, André
%Y Lampouras, Gerasimos
%Y Lyu, Chunchuan
%S Proceedings of the Sixth Workshop on Structured Prediction for NLP
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F daza-etal-2022-slotgan
%X We present SlotGAN, a framework for training a mention detection model that only requires unlabeled text and a gazetteer. It consists of a generator trained to extract spans from an input sentence, and a discriminator trained to determine whether a span comes from the generator, or from the gazetteer. We evaluate the method on English newswire data and compare it against supervised, weakly-supervised, and unsupervised methods. We find that the performance of the method is lower than these baselines, because it tends to generate more and longer spans, and in some cases it relies only on capitalization. In other cases, it generates spans that are valid but differ from the benchmark. When evaluated with metrics based on overlap, we find that SlotGAN performs within 95% of the precision of a supervised method, and 84% of its recall. Our results suggest that the model can generate spans that overlap well, but an additional filtering mechanism is required.
%R 10.18653/v1/2022.spnlp-1.4
%U https://aclanthology.org/2022.spnlp-1.4
%U https://doi.org/10.18653/v1/2022.spnlp-1.4
%P 32-39
Markdown (Informal)
[SlotGAN: Detecting Mentions in Text via Adversarial Distant Learning](https://aclanthology.org/2022.spnlp-1.4) (Daza et al., spnlp 2022)
ACL