@inproceedings{bakshi-sharma-2021-transformer,
title = "A Transformer Based Approach towards Identification of Discourse Unit Segments and Connectives",
author = "Bakshi, Sahil and
Sharma, Dipti",
editor = "Zeldes, Amir and
Liu, Yang Janet and
Iruskieta, Mikel and
Muller, Philippe and
Braud, Chlo{\'e} and
Badene, Sonia",
booktitle = "Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021)",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.disrpt-1.2",
doi = "10.18653/v1/2021.disrpt-1.2",
pages = "13--21",
abstract = "Discourse parsing, which involves understanding the structure, information flow, and modeling the coherence of a given text, is an important task in natural language processing. It forms the basis of several natural language processing tasks such as question-answering, text summarization, and sentiment analysis. Discourse unit segmentation is one of the fundamental tasks in discourse parsing and refers to identifying the elementary units of text that combine to form a coherent text. In this paper, we present a transformer based approach towards the automated identification of discourse unit segments and connectives. Early approaches towards segmentation relied on rule-based systems using POS tags and other syntactic information to identify discourse segments. Recently, transformer based neural systems have shown promising results in this domain. Our system, SegFormers, employs this transformer based approach to perform multilingual discourse segmentation and connective identification across 16 datasets encompassing 11 languages and 3 different annotation frameworks. We evaluate the system based on F1 scores for both tasks, with the best system reporting the highest F1 score of 97.02{\%} for the treebanked English RST-DT dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bakshi-sharma-2021-transformer">
<titleInfo>
<title>A Transformer Based Approach towards Identification of Discourse Unit Segments and Connectives</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sahil</namePart>
<namePart type="family">Bakshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="family">Sharma</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 Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zeldes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">Janet</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Iruskieta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Muller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Sonia</namePart>
<namePart type="family">Badene</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</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Discourse parsing, which involves understanding the structure, information flow, and modeling the coherence of a given text, is an important task in natural language processing. It forms the basis of several natural language processing tasks such as question-answering, text summarization, and sentiment analysis. Discourse unit segmentation is one of the fundamental tasks in discourse parsing and refers to identifying the elementary units of text that combine to form a coherent text. In this paper, we present a transformer based approach towards the automated identification of discourse unit segments and connectives. Early approaches towards segmentation relied on rule-based systems using POS tags and other syntactic information to identify discourse segments. Recently, transformer based neural systems have shown promising results in this domain. Our system, SegFormers, employs this transformer based approach to perform multilingual discourse segmentation and connective identification across 16 datasets encompassing 11 languages and 3 different annotation frameworks. We evaluate the system based on F1 scores for both tasks, with the best system reporting the highest F1 score of 97.02% for the treebanked English RST-DT dataset.</abstract>
<identifier type="citekey">bakshi-sharma-2021-transformer</identifier>
<identifier type="doi">10.18653/v1/2021.disrpt-1.2</identifier>
<location>
<url>https://aclanthology.org/2021.disrpt-1.2</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>13</start>
<end>21</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Transformer Based Approach towards Identification of Discourse Unit Segments and Connectives
%A Bakshi, Sahil
%A Sharma, Dipti
%Y Zeldes, Amir
%Y Liu, Yang Janet
%Y Iruskieta, Mikel
%Y Muller, Philippe
%Y Braud, Chloé
%Y Badene, Sonia
%S Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021)
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F bakshi-sharma-2021-transformer
%X Discourse parsing, which involves understanding the structure, information flow, and modeling the coherence of a given text, is an important task in natural language processing. It forms the basis of several natural language processing tasks such as question-answering, text summarization, and sentiment analysis. Discourse unit segmentation is one of the fundamental tasks in discourse parsing and refers to identifying the elementary units of text that combine to form a coherent text. In this paper, we present a transformer based approach towards the automated identification of discourse unit segments and connectives. Early approaches towards segmentation relied on rule-based systems using POS tags and other syntactic information to identify discourse segments. Recently, transformer based neural systems have shown promising results in this domain. Our system, SegFormers, employs this transformer based approach to perform multilingual discourse segmentation and connective identification across 16 datasets encompassing 11 languages and 3 different annotation frameworks. We evaluate the system based on F1 scores for both tasks, with the best system reporting the highest F1 score of 97.02% for the treebanked English RST-DT dataset.
%R 10.18653/v1/2021.disrpt-1.2
%U https://aclanthology.org/2021.disrpt-1.2
%U https://doi.org/10.18653/v1/2021.disrpt-1.2
%P 13-21
Markdown (Informal)
[A Transformer Based Approach towards Identification of Discourse Unit Segments and Connectives](https://aclanthology.org/2021.disrpt-1.2) (Bakshi & Sharma, DISRPT 2021)
ACL