@inproceedings{elaraby-litman-2021-self,
title = "Self-trained Pretrained Language Models for Evidence Detection",
author = "Elaraby, Mohamed and
Litman, Diane",
editor = "Al-Khatib, Khalid and
Hou, Yufang and
Stede, Manfred",
booktitle = "Proceedings of the 8th Workshop on Argument Mining",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.argmining-1.14",
doi = "10.18653/v1/2021.argmining-1.14",
pages = "142--147",
abstract = "Argument role labeling is a fundamental task in Argument Mining research. However, such research often suffers from a lack of large-scale datasets labeled for argument roles such as evidence, which is crucial for neural model training. While large pretrained language models have somewhat alleviated the need for massive manually labeled datasets, how much these models can further benefit from self-training techniques hasn{'}t been widely explored in the literature in general and in Argument Mining specifically. In this work, we focus on self-trained language models (particularly BERT) for evidence detection. We provide a thorough investigation on how to utilize pseudo labels effectively in the self-training scheme. We also assess whether adding pseudo labels from an out-of-domain source can be beneficial. Experiments on sentence level evidence detection show that self-training can complement pretrained language models to provide performance improvements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elaraby-litman-2021-self">
<titleInfo>
<title>Self-trained Pretrained Language Models for Evidence Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Elaraby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diane</namePart>
<namePart type="family">Litman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Argument Mining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Al-Khatib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufang</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manfred</namePart>
<namePart type="family">Stede</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Argument role labeling is a fundamental task in Argument Mining research. However, such research often suffers from a lack of large-scale datasets labeled for argument roles such as evidence, which is crucial for neural model training. While large pretrained language models have somewhat alleviated the need for massive manually labeled datasets, how much these models can further benefit from self-training techniques hasn’t been widely explored in the literature in general and in Argument Mining specifically. In this work, we focus on self-trained language models (particularly BERT) for evidence detection. We provide a thorough investigation on how to utilize pseudo labels effectively in the self-training scheme. We also assess whether adding pseudo labels from an out-of-domain source can be beneficial. Experiments on sentence level evidence detection show that self-training can complement pretrained language models to provide performance improvements.</abstract>
<identifier type="citekey">elaraby-litman-2021-self</identifier>
<identifier type="doi">10.18653/v1/2021.argmining-1.14</identifier>
<location>
<url>https://aclanthology.org/2021.argmining-1.14</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>142</start>
<end>147</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-trained Pretrained Language Models for Evidence Detection
%A Elaraby, Mohamed
%A Litman, Diane
%Y Al-Khatib, Khalid
%Y Hou, Yufang
%Y Stede, Manfred
%S Proceedings of the 8th Workshop on Argument Mining
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F elaraby-litman-2021-self
%X Argument role labeling is a fundamental task in Argument Mining research. However, such research often suffers from a lack of large-scale datasets labeled for argument roles such as evidence, which is crucial for neural model training. While large pretrained language models have somewhat alleviated the need for massive manually labeled datasets, how much these models can further benefit from self-training techniques hasn’t been widely explored in the literature in general and in Argument Mining specifically. In this work, we focus on self-trained language models (particularly BERT) for evidence detection. We provide a thorough investigation on how to utilize pseudo labels effectively in the self-training scheme. We also assess whether adding pseudo labels from an out-of-domain source can be beneficial. Experiments on sentence level evidence detection show that self-training can complement pretrained language models to provide performance improvements.
%R 10.18653/v1/2021.argmining-1.14
%U https://aclanthology.org/2021.argmining-1.14
%U https://doi.org/10.18653/v1/2021.argmining-1.14
%P 142-147
Markdown (Informal)
[Self-trained Pretrained Language Models for Evidence Detection](https://aclanthology.org/2021.argmining-1.14) (Elaraby & Litman, ArgMining 2021)
ACL