@inproceedings{zhang-etal-2021-domain,
title = "Can Domain Pre-training Help Interdisciplinary Researchers from Data Annotation Poverty? A Case Study of Legal Argument Mining with {BERT}-based Transformers",
author = "Zhang, Gechuan and
Lillis, David and
Nulty, Paul",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
Alnajjar, Khalid and
Partanen, Niko and
Rueter, Jack},
booktitle = "Proceedings of the Workshop on Natural Language Processing for Digital Humanities",
month = dec,
year = "2021",
address = "NIT Silchar, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2021.nlp4dh-1.14",
pages = "121--130",
abstract = "Interdisciplinary Natural Language Processing (NLP) research traditionally suffers from the requirement for costly data annotation. However, transformer frameworks with pre-training have shown their ability on many downstream tasks including digital humanities tasks with limited small datasets. Considering the fact that many digital humanities fields (e.g. law) feature an abundance of non-annotated textual resources, and the recent achievements led by transformer models, we pay special attention to whether domain pre-training will enhance transformer{'}s performance on interdisciplinary tasks and how. In this work, we use legal argument mining as our case study. This aims to automatically identify text segments with particular linguistic structures (i.e., arguments) from legal documents and to predict the reasoning relations between marked arguments. Our work includes a broad survey of a wide range of BERT variants with different pre-training strategies. Our case study focuses on: the comparison of general pre-training and domain pre-training; the generalisability of different domain pre-trained transformers; and the potential of merging general pre-training with domain pre-training. We also achieve better results than the current transformer baseline in legal argument mining.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2021-domain">
<titleInfo>
<title>Can Domain Pre-training Help Interdisciplinary Researchers from Data Annotation Poverty? A Case Study of Legal Argument Mining with BERT-based Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gechuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Lillis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Nulty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Natural Language Processing for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niko</namePart>
<namePart type="family">Partanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Rueter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">NIT Silchar, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Interdisciplinary Natural Language Processing (NLP) research traditionally suffers from the requirement for costly data annotation. However, transformer frameworks with pre-training have shown their ability on many downstream tasks including digital humanities tasks with limited small datasets. Considering the fact that many digital humanities fields (e.g. law) feature an abundance of non-annotated textual resources, and the recent achievements led by transformer models, we pay special attention to whether domain pre-training will enhance transformer’s performance on interdisciplinary tasks and how. In this work, we use legal argument mining as our case study. This aims to automatically identify text segments with particular linguistic structures (i.e., arguments) from legal documents and to predict the reasoning relations between marked arguments. Our work includes a broad survey of a wide range of BERT variants with different pre-training strategies. Our case study focuses on: the comparison of general pre-training and domain pre-training; the generalisability of different domain pre-trained transformers; and the potential of merging general pre-training with domain pre-training. We also achieve better results than the current transformer baseline in legal argument mining.</abstract>
<identifier type="citekey">zhang-etal-2021-domain</identifier>
<location>
<url>https://aclanthology.org/2021.nlp4dh-1.14</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>121</start>
<end>130</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Domain Pre-training Help Interdisciplinary Researchers from Data Annotation Poverty? A Case Study of Legal Argument Mining with BERT-based Transformers
%A Zhang, Gechuan
%A Lillis, David
%A Nulty, Paul
%Y Hämäläinen, Mika
%Y Alnajjar, Khalid
%Y Partanen, Niko
%Y Rueter, Jack
%S Proceedings of the Workshop on Natural Language Processing for Digital Humanities
%D 2021
%8 December
%I NLP Association of India (NLPAI)
%C NIT Silchar, India
%F zhang-etal-2021-domain
%X Interdisciplinary Natural Language Processing (NLP) research traditionally suffers from the requirement for costly data annotation. However, transformer frameworks with pre-training have shown their ability on many downstream tasks including digital humanities tasks with limited small datasets. Considering the fact that many digital humanities fields (e.g. law) feature an abundance of non-annotated textual resources, and the recent achievements led by transformer models, we pay special attention to whether domain pre-training will enhance transformer’s performance on interdisciplinary tasks and how. In this work, we use legal argument mining as our case study. This aims to automatically identify text segments with particular linguistic structures (i.e., arguments) from legal documents and to predict the reasoning relations between marked arguments. Our work includes a broad survey of a wide range of BERT variants with different pre-training strategies. Our case study focuses on: the comparison of general pre-training and domain pre-training; the generalisability of different domain pre-trained transformers; and the potential of merging general pre-training with domain pre-training. We also achieve better results than the current transformer baseline in legal argument mining.
%U https://aclanthology.org/2021.nlp4dh-1.14
%P 121-130
Markdown (Informal)
[Can Domain Pre-training Help Interdisciplinary Researchers from Data Annotation Poverty? A Case Study of Legal Argument Mining with BERT-based Transformers](https://aclanthology.org/2021.nlp4dh-1.14) (Zhang et al., NLP4DH 2021)
ACL