@inproceedings{lee-etal-2023-side,
title = "A Side-by-side Comparison of Transformers for Implicit Discourse Relation Classification",
author = "Lee, Bruce W. and
Yang, Bongseok and
Lee, Jason",
editor = "Strube, Michael and
Braud, Chloe and
Hardmeier, Christian and
Li, Junyi Jessy and
Loaiciga, Sharid and
Zeldes, Amir",
booktitle = "Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.codi-1.2",
doi = "10.18653/v1/2023.codi-1.2",
pages = "16--23",
abstract = "Though discourse parsing can help multiple NLP fields, there has been no wide language model search done on implicit discourse relation classification. This hinders researchers from fully utilizing public-available models in discourse analysis. This work is a straightforward, fine-tuned discourse performance comparison of 7 pre-trained language models. We use PDTB-3, a popular discourse relation annotated dataset. Through our model search, we raise SOTA to 0.671 ACC and obtain novel observations. Some are contrary to what has been reported before (Shi and Demberg, 2019b), that sentence-level pre-training objectives (NSP, SBO, SOP) generally fail to produce the best-performing model for implicit discourse relation classification. Counterintuitively, similar-sized PLMs with MLM and full attention led to better performance. Our code is publicly released.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2023-side">
<titleInfo>
<title>A Side-by-side Comparison of Transformers for Implicit Discourse Relation Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bruce</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bongseok</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Lee</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>Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Strube</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chloe</namePart>
<namePart type="family">Braud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharid</namePart>
<namePart type="family">Loaiciga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zeldes</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>Though discourse parsing can help multiple NLP fields, there has been no wide language model search done on implicit discourse relation classification. This hinders researchers from fully utilizing public-available models in discourse analysis. This work is a straightforward, fine-tuned discourse performance comparison of 7 pre-trained language models. We use PDTB-3, a popular discourse relation annotated dataset. Through our model search, we raise SOTA to 0.671 ACC and obtain novel observations. Some are contrary to what has been reported before (Shi and Demberg, 2019b), that sentence-level pre-training objectives (NSP, SBO, SOP) generally fail to produce the best-performing model for implicit discourse relation classification. Counterintuitively, similar-sized PLMs with MLM and full attention led to better performance. Our code is publicly released.</abstract>
<identifier type="citekey">lee-etal-2023-side</identifier>
<identifier type="doi">10.18653/v1/2023.codi-1.2</identifier>
<location>
<url>https://aclanthology.org/2023.codi-1.2</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>16</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Side-by-side Comparison of Transformers for Implicit Discourse Relation Classification
%A Lee, Bruce W.
%A Yang, Bongseok
%A Lee, Jason
%Y Strube, Michael
%Y Braud, Chloe
%Y Hardmeier, Christian
%Y Li, Junyi Jessy
%Y Loaiciga, Sharid
%Y Zeldes, Amir
%S Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F lee-etal-2023-side
%X Though discourse parsing can help multiple NLP fields, there has been no wide language model search done on implicit discourse relation classification. This hinders researchers from fully utilizing public-available models in discourse analysis. This work is a straightforward, fine-tuned discourse performance comparison of 7 pre-trained language models. We use PDTB-3, a popular discourse relation annotated dataset. Through our model search, we raise SOTA to 0.671 ACC and obtain novel observations. Some are contrary to what has been reported before (Shi and Demberg, 2019b), that sentence-level pre-training objectives (NSP, SBO, SOP) generally fail to produce the best-performing model for implicit discourse relation classification. Counterintuitively, similar-sized PLMs with MLM and full attention led to better performance. Our code is publicly released.
%R 10.18653/v1/2023.codi-1.2
%U https://aclanthology.org/2023.codi-1.2
%U https://doi.org/10.18653/v1/2023.codi-1.2
%P 16-23
Markdown (Informal)
[A Side-by-side Comparison of Transformers for Implicit Discourse Relation Classification](https://aclanthology.org/2023.codi-1.2) (Lee et al., CODI 2023)
ACL