@inproceedings{muther-smith-2020-tracing,
title = "Tracing Traditions: Automatic Extraction of Isnads from Classical {A}rabic Texts",
author = "Muther, Ryan and
Smith, David",
editor = "Zitouni, Imed and
Abdul-Mageed, Muhammad and
Bouamor, Houda and
Bougares, Fethi and
El-Haj, Mahmoud and
Tomeh, Nadi and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Fifth Arabic Natural Language Processing Workshop",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wanlp-1.12/",
pages = "130--138",
abstract = "We present our work on automatically detecting isnads, the chains of authorities for a re-port that serve as citations in hadith and other classical Arabic texts. We experiment with both sequence labeling methods for identifying isnads in a single pass and a hybrid {\textquotedblleft}retrieve-and-tag{\textquotedblright} approach, in which a retrieval model first identifies portions of the text that are likely to contain start points for isnads, then a sequence labeling model identifies the exact starting locations within these much smaller retrieved text chunks. We find that the usefulness of full-document sequence to sequence models is limited due to memory limitations and the ineffectiveness of such models at modeling very long documents. We conclude by sketching future improvements on the tagging task and more in-depth analysis of the people and relationships involved in the social network that influenced the evolution of the written tradition over time."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="muther-smith-2020-tracing">
<titleInfo>
<title>Tracing Traditions: Automatic Extraction of Isnads from Classical Arabic Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Muther</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present our work on automatically detecting isnads, the chains of authorities for a re-port that serve as citations in hadith and other classical Arabic texts. We experiment with both sequence labeling methods for identifying isnads in a single pass and a hybrid “retrieve-and-tag” approach, in which a retrieval model first identifies portions of the text that are likely to contain start points for isnads, then a sequence labeling model identifies the exact starting locations within these much smaller retrieved text chunks. We find that the usefulness of full-document sequence to sequence models is limited due to memory limitations and the ineffectiveness of such models at modeling very long documents. We conclude by sketching future improvements on the tagging task and more in-depth analysis of the people and relationships involved in the social network that influenced the evolution of the written tradition over time.</abstract>
<identifier type="citekey">muther-smith-2020-tracing</identifier>
<location>
<url>https://aclanthology.org/2020.wanlp-1.12/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>130</start>
<end>138</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tracing Traditions: Automatic Extraction of Isnads from Classical Arabic Texts
%A Muther, Ryan
%A Smith, David
%Y Zitouni, Imed
%Y Abdul-Mageed, Muhammad
%Y Bouamor, Houda
%Y Bougares, Fethi
%Y El-Haj, Mahmoud
%Y Tomeh, Nadi
%Y Zaghouani, Wajdi
%S Proceedings of the Fifth Arabic Natural Language Processing Workshop
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F muther-smith-2020-tracing
%X We present our work on automatically detecting isnads, the chains of authorities for a re-port that serve as citations in hadith and other classical Arabic texts. We experiment with both sequence labeling methods for identifying isnads in a single pass and a hybrid “retrieve-and-tag” approach, in which a retrieval model first identifies portions of the text that are likely to contain start points for isnads, then a sequence labeling model identifies the exact starting locations within these much smaller retrieved text chunks. We find that the usefulness of full-document sequence to sequence models is limited due to memory limitations and the ineffectiveness of such models at modeling very long documents. We conclude by sketching future improvements on the tagging task and more in-depth analysis of the people and relationships involved in the social network that influenced the evolution of the written tradition over time.
%U https://aclanthology.org/2020.wanlp-1.12/
%P 130-138
Markdown (Informal)
[Tracing Traditions: Automatic Extraction of Isnads from Classical Arabic Texts](https://aclanthology.org/2020.wanlp-1.12/) (Muther & Smith, WANLP 2020)
ACL