@inproceedings{yu-etal-2022-rst,
title = "{RST} Discourse Parsing with Second-Stage {EDU}-Level Pre-training",
author = "Yu, Nan and
Zhang, Meishan and
Fu, Guohong and
Zhang, Min",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.294",
doi = "10.18653/v1/2022.acl-long.294",
pages = "4269--4280",
abstract = "Pre-trained language models (PLMs) have shown great potentials in natural language processing (NLP) including rhetorical structure theory (RST) discourse parsing. Current PLMs are obtained by sentence-level pre-training, which is different from the basic processing unit, i.e. element discourse unit (EDU).To this end, we propose a second-stage EDU-level pre-training approach in this work, which presents two novel tasks to learn effective EDU representations continually based on well pre-trained language models. Concretely, the two tasks are (1) next EDU prediction (NEP) and (2) discourse marker prediction (DMP).We take a state-of-the-art transition-based neural parser as baseline, and adopt it with a light bi-gram EDU modification to effectively explore the EDU-level pre-trained EDU representation. Experimental results on a benckmark dataset show that our method is highly effective,leading a 2.1-point improvement in F1-score. All codes and pre-trained models will be released publicly to facilitate future studies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2022-rst">
<titleInfo>
<title>RST Discourse Parsing with Second-Stage EDU-Level Pre-training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meishan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guohong</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</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 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</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>Pre-trained language models (PLMs) have shown great potentials in natural language processing (NLP) including rhetorical structure theory (RST) discourse parsing. Current PLMs are obtained by sentence-level pre-training, which is different from the basic processing unit, i.e. element discourse unit (EDU).To this end, we propose a second-stage EDU-level pre-training approach in this work, which presents two novel tasks to learn effective EDU representations continually based on well pre-trained language models. Concretely, the two tasks are (1) next EDU prediction (NEP) and (2) discourse marker prediction (DMP).We take a state-of-the-art transition-based neural parser as baseline, and adopt it with a light bi-gram EDU modification to effectively explore the EDU-level pre-trained EDU representation. Experimental results on a benckmark dataset show that our method is highly effective,leading a 2.1-point improvement in F1-score. All codes and pre-trained models will be released publicly to facilitate future studies.</abstract>
<identifier type="citekey">yu-etal-2022-rst</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.294</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.294</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>4269</start>
<end>4280</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RST Discourse Parsing with Second-Stage EDU-Level Pre-training
%A Yu, Nan
%A Zhang, Meishan
%A Fu, Guohong
%A Zhang, Min
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F yu-etal-2022-rst
%X Pre-trained language models (PLMs) have shown great potentials in natural language processing (NLP) including rhetorical structure theory (RST) discourse parsing. Current PLMs are obtained by sentence-level pre-training, which is different from the basic processing unit, i.e. element discourse unit (EDU).To this end, we propose a second-stage EDU-level pre-training approach in this work, which presents two novel tasks to learn effective EDU representations continually based on well pre-trained language models. Concretely, the two tasks are (1) next EDU prediction (NEP) and (2) discourse marker prediction (DMP).We take a state-of-the-art transition-based neural parser as baseline, and adopt it with a light bi-gram EDU modification to effectively explore the EDU-level pre-trained EDU representation. Experimental results on a benckmark dataset show that our method is highly effective,leading a 2.1-point improvement in F1-score. All codes and pre-trained models will be released publicly to facilitate future studies.
%R 10.18653/v1/2022.acl-long.294
%U https://aclanthology.org/2022.acl-long.294
%U https://doi.org/10.18653/v1/2022.acl-long.294
%P 4269-4280
Markdown (Informal)
[RST Discourse Parsing with Second-Stage EDU-Level Pre-training](https://aclanthology.org/2022.acl-long.294) (Yu et al., ACL 2022)
ACL
- Nan Yu, Meishan Zhang, Guohong Fu, and Min Zhang. 2022. RST Discourse Parsing with Second-Stage EDU-Level Pre-training. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4269–4280, Dublin, Ireland. Association for Computational Linguistics.