@inproceedings{scholman-etal-2021-comparison,
title = "Comparison of methods for explicit discourse connective identification across various domains",
author = "Scholman, Merel and
Dong, Tianai and
Yung, Frances and
Demberg, Vera",
editor = "Braud, Chlo{\'e} and
Hardmeier, Christian and
Li, Junyi Jessy and
Louis, Annie and
Strube, Michael and
Zeldes, Amir",
booktitle = "Proceedings of the 2nd Workshop on Computational Approaches to Discourse",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic and Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.codi-main.9",
doi = "10.18653/v1/2021.codi-main.9",
pages = "95--106",
abstract = "Existing parse methods use varying approaches to identify explicit discourse connectives, but their performance has not been consistently evaluated in comparison to each other, nor have they been evaluated consistently on text other than newspaper articles. We here assess the performance on explicit connective identification of three parse methods (PDTB e2e, Lin et al., 2014; the winner of CONLL2015, Wang et al., 2015; and DisSent, Nie et al., 2019), along with a simple heuristic. We also examine how well these systems generalize to different datasets, namely written newspaper text (PDTB), written scientific text (BioDRB), prepared spoken text (TED-MDB) and spontaneous spoken text (Disco-SPICE). The results show that the e2e parser outperforms the other parse methods in all datasets. However, performance drops significantly from the PDTB to all other datasets. We provide a more fine-grained analysis of domain differences and connectives that prove difficult to parse, in order to highlight the areas where gains can be made.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scholman-etal-2021-comparison">
<titleInfo>
<title>Comparison of methods for explicit discourse connective identification across various domains</title>
</titleInfo>
<name type="personal">
<namePart type="given">Merel</namePart>
<namePart type="family">Scholman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianai</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frances</namePart>
<namePart type="family">Yung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</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 2nd Workshop on Computational Approaches to Discourse</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chloé</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">Annie</namePart>
<namePart type="family">Louis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">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">Punta Cana, Dominican Republic and Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing parse methods use varying approaches to identify explicit discourse connectives, but their performance has not been consistently evaluated in comparison to each other, nor have they been evaluated consistently on text other than newspaper articles. We here assess the performance on explicit connective identification of three parse methods (PDTB e2e, Lin et al., 2014; the winner of CONLL2015, Wang et al., 2015; and DisSent, Nie et al., 2019), along with a simple heuristic. We also examine how well these systems generalize to different datasets, namely written newspaper text (PDTB), written scientific text (BioDRB), prepared spoken text (TED-MDB) and spontaneous spoken text (Disco-SPICE). The results show that the e2e parser outperforms the other parse methods in all datasets. However, performance drops significantly from the PDTB to all other datasets. We provide a more fine-grained analysis of domain differences and connectives that prove difficult to parse, in order to highlight the areas where gains can be made.</abstract>
<identifier type="citekey">scholman-etal-2021-comparison</identifier>
<identifier type="doi">10.18653/v1/2021.codi-main.9</identifier>
<location>
<url>https://aclanthology.org/2021.codi-main.9</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>95</start>
<end>106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparison of methods for explicit discourse connective identification across various domains
%A Scholman, Merel
%A Dong, Tianai
%A Yung, Frances
%A Demberg, Vera
%Y Braud, Chloé
%Y Hardmeier, Christian
%Y Li, Junyi Jessy
%Y Louis, Annie
%Y Strube, Michael
%Y Zeldes, Amir
%S Proceedings of the 2nd Workshop on Computational Approaches to Discourse
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic and Online
%F scholman-etal-2021-comparison
%X Existing parse methods use varying approaches to identify explicit discourse connectives, but their performance has not been consistently evaluated in comparison to each other, nor have they been evaluated consistently on text other than newspaper articles. We here assess the performance on explicit connective identification of three parse methods (PDTB e2e, Lin et al., 2014; the winner of CONLL2015, Wang et al., 2015; and DisSent, Nie et al., 2019), along with a simple heuristic. We also examine how well these systems generalize to different datasets, namely written newspaper text (PDTB), written scientific text (BioDRB), prepared spoken text (TED-MDB) and spontaneous spoken text (Disco-SPICE). The results show that the e2e parser outperforms the other parse methods in all datasets. However, performance drops significantly from the PDTB to all other datasets. We provide a more fine-grained analysis of domain differences and connectives that prove difficult to parse, in order to highlight the areas where gains can be made.
%R 10.18653/v1/2021.codi-main.9
%U https://aclanthology.org/2021.codi-main.9
%U https://doi.org/10.18653/v1/2021.codi-main.9
%P 95-106
Markdown (Informal)
[Comparison of methods for explicit discourse connective identification across various domains](https://aclanthology.org/2021.codi-main.9) (Scholman et al., CODI 2021)
ACL