@inproceedings{banisakher-etal-2020-improving,
title = "Improving the Identification of the Discourse Function of News Article Paragraphs",
author = "Banisakher, Deya and
Yarlott, W. Victor and
Aldawsari, Mohammed and
Rishe, Naphtali and
Finlayson, Mark",
editor = "Bonial, Claire and
Caselli, Tommaso and
Chaturvedi, Snigdha and
Clark, Elizabeth and
Huang, Ruihong and
Iyyer, Mohit and
Jaimes, Alejandro and
Ji, Heng and
Martin, Lara J. and
Miller, Ben and
Mitamura, Teruko and
Peng, Nanyun and
Tetreault, Joel",
booktitle = "Proceedings of the First Joint Workshop on Narrative Understanding, Storylines, and Events",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nuse-1.3",
doi = "10.18653/v1/2020.nuse-1.3",
pages = "17--25",
abstract = "Identifying the discourse structure of documents is an important task in understanding written text. Building on prior work, we demonstrate an improved approach to automatically identifying the discourse function of paragraphs in news articles. We start with the hierarchical theory of news discourse developed by van Dijk (1988) which proposes how paragraphs function within news articles. This discourse information is a level intermediate between phrase- or sentence-sized discourse segments and document genre, characterizing how individual paragraphs convey information about the events in the storyline of the article. Specifically, the theory categorizes the relationships between narrated events and (1) the overall storyline (such as Main Events, Background, or Consequences) as well as (2) commentary (such as Verbal Reactions and Evaluations). We trained and tested a linear chain conditional random field (CRF) with new features to model van Dijk{'}s labels and compared it against several machine learning models presented in previous work. Our model significantly outperformed all baselines and prior approaches, achieving an average of 0.71 F1 score which represents a 31.5{\%} improvement over the previously best-performing support vector machine model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="banisakher-etal-2020-improving">
<titleInfo>
<title>Improving the Identification of the Discourse Function of News Article Paragraphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deya</namePart>
<namePart type="family">Banisakher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">W</namePart>
<namePart type="given">Victor</namePart>
<namePart type="family">Yarlott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Aldawsari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naphtali</namePart>
<namePart type="family">Rishe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Finlayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Joint Workshop on Narrative Understanding, Storylines, and Events</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Bonial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommaso</namePart>
<namePart type="family">Caselli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Snigdha</namePart>
<namePart type="family">Chaturvedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruihong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Iyyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alejandro</namePart>
<namePart type="family">Jaimes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lara</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Miller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teruko</namePart>
<namePart type="family">Mitamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Identifying the discourse structure of documents is an important task in understanding written text. Building on prior work, we demonstrate an improved approach to automatically identifying the discourse function of paragraphs in news articles. We start with the hierarchical theory of news discourse developed by van Dijk (1988) which proposes how paragraphs function within news articles. This discourse information is a level intermediate between phrase- or sentence-sized discourse segments and document genre, characterizing how individual paragraphs convey information about the events in the storyline of the article. Specifically, the theory categorizes the relationships between narrated events and (1) the overall storyline (such as Main Events, Background, or Consequences) as well as (2) commentary (such as Verbal Reactions and Evaluations). We trained and tested a linear chain conditional random field (CRF) with new features to model van Dijk’s labels and compared it against several machine learning models presented in previous work. Our model significantly outperformed all baselines and prior approaches, achieving an average of 0.71 F1 score which represents a 31.5% improvement over the previously best-performing support vector machine model.</abstract>
<identifier type="citekey">banisakher-etal-2020-improving</identifier>
<identifier type="doi">10.18653/v1/2020.nuse-1.3</identifier>
<location>
<url>https://aclanthology.org/2020.nuse-1.3</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>17</start>
<end>25</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving the Identification of the Discourse Function of News Article Paragraphs
%A Banisakher, Deya
%A Yarlott, W. Victor
%A Aldawsari, Mohammed
%A Rishe, Naphtali
%A Finlayson, Mark
%Y Bonial, Claire
%Y Caselli, Tommaso
%Y Chaturvedi, Snigdha
%Y Clark, Elizabeth
%Y Huang, Ruihong
%Y Iyyer, Mohit
%Y Jaimes, Alejandro
%Y Ji, Heng
%Y Martin, Lara J.
%Y Miller, Ben
%Y Mitamura, Teruko
%Y Peng, Nanyun
%Y Tetreault, Joel
%S Proceedings of the First Joint Workshop on Narrative Understanding, Storylines, and Events
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F banisakher-etal-2020-improving
%X Identifying the discourse structure of documents is an important task in understanding written text. Building on prior work, we demonstrate an improved approach to automatically identifying the discourse function of paragraphs in news articles. We start with the hierarchical theory of news discourse developed by van Dijk (1988) which proposes how paragraphs function within news articles. This discourse information is a level intermediate between phrase- or sentence-sized discourse segments and document genre, characterizing how individual paragraphs convey information about the events in the storyline of the article. Specifically, the theory categorizes the relationships between narrated events and (1) the overall storyline (such as Main Events, Background, or Consequences) as well as (2) commentary (such as Verbal Reactions and Evaluations). We trained and tested a linear chain conditional random field (CRF) with new features to model van Dijk’s labels and compared it against several machine learning models presented in previous work. Our model significantly outperformed all baselines and prior approaches, achieving an average of 0.71 F1 score which represents a 31.5% improvement over the previously best-performing support vector machine model.
%R 10.18653/v1/2020.nuse-1.3
%U https://aclanthology.org/2020.nuse-1.3
%U https://doi.org/10.18653/v1/2020.nuse-1.3
%P 17-25
Markdown (Informal)
[Improving the Identification of the Discourse Function of News Article Paragraphs](https://aclanthology.org/2020.nuse-1.3) (Banisakher et al., NUSE-WNU 2020)
ACL