@inproceedings{alharbi-al-muhtasab-2022-arabic,
title = "{A}rabic Keyphrase Extraction: Enhancing Deep Learning Models with Pre-trained Contextual Embedding and External Features",
author = "Alharbi, Randah and
Al-Muhtasab, Husni",
editor = "Bouamor, Houda and
Al-Khalifa, Hend and
Darwish, Kareem and
Rambow, Owen and
Bougares, Fethi and
Abdelali, Ahmed and
Tomeh, Nadi and
Khalifa, Salam and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wanlp-1.30/",
doi = "10.18653/v1/2022.wanlp-1.30",
pages = "320--330",
abstract = "Keyphrase extraction is essential to many Information retrieval (IR) and Natural language Processing (NLP) tasks such as summarization and indexing. This study investigates deep learning approaches to Arabic keyphrase extraction. We address the problem as sequence classification and create a Bi-LSTM model to classify each sequence token as either part of the keyphrase or outside of it. We have extracted word embeddings from two pre-trained models, Word2Vec and BERT. Moreover, we have investigated the effect of incorporating linguistic, positional, and statistical features with word embeddings on performance. Our best-performing model has achieved 0.45 F1-score on ArabicKPE dataset when combining linguistic and positional features with BERT embedding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alharbi-al-muhtasab-2022-arabic">
<titleInfo>
<title>Arabic Keyphrase Extraction: Enhancing Deep Learning Models with Pre-trained Contextual Embedding and External Features</title>
</titleInfo>
<name type="personal">
<namePart type="given">Randah</namePart>
<namePart type="family">Alharbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Husni</namePart>
<namePart type="family">Al-Muhtasab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)</title>
</titleInfo>
<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">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</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">Ahmed</namePart>
<namePart type="family">Abdelali</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">Salam</namePart>
<namePart type="family">Khalifa</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">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Keyphrase extraction is essential to many Information retrieval (IR) and Natural language Processing (NLP) tasks such as summarization and indexing. This study investigates deep learning approaches to Arabic keyphrase extraction. We address the problem as sequence classification and create a Bi-LSTM model to classify each sequence token as either part of the keyphrase or outside of it. We have extracted word embeddings from two pre-trained models, Word2Vec and BERT. Moreover, we have investigated the effect of incorporating linguistic, positional, and statistical features with word embeddings on performance. Our best-performing model has achieved 0.45 F1-score on ArabicKPE dataset when combining linguistic and positional features with BERT embedding.</abstract>
<identifier type="citekey">alharbi-al-muhtasab-2022-arabic</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.30</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.30/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>320</start>
<end>330</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Keyphrase Extraction: Enhancing Deep Learning Models with Pre-trained Contextual Embedding and External Features
%A Alharbi, Randah
%A Al-Muhtasab, Husni
%Y Bouamor, Houda
%Y Al-Khalifa, Hend
%Y Darwish, Kareem
%Y Rambow, Owen
%Y Bougares, Fethi
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Khalifa, Salam
%Y Zaghouani, Wajdi
%S Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F alharbi-al-muhtasab-2022-arabic
%X Keyphrase extraction is essential to many Information retrieval (IR) and Natural language Processing (NLP) tasks such as summarization and indexing. This study investigates deep learning approaches to Arabic keyphrase extraction. We address the problem as sequence classification and create a Bi-LSTM model to classify each sequence token as either part of the keyphrase or outside of it. We have extracted word embeddings from two pre-trained models, Word2Vec and BERT. Moreover, we have investigated the effect of incorporating linguistic, positional, and statistical features with word embeddings on performance. Our best-performing model has achieved 0.45 F1-score on ArabicKPE dataset when combining linguistic and positional features with BERT embedding.
%R 10.18653/v1/2022.wanlp-1.30
%U https://aclanthology.org/2022.wanlp-1.30/
%U https://doi.org/10.18653/v1/2022.wanlp-1.30
%P 320-330
Markdown (Informal)
[Arabic Keyphrase Extraction: Enhancing Deep Learning Models with Pre-trained Contextual Embedding and External Features](https://aclanthology.org/2022.wanlp-1.30/) (Alharbi & Al-Muhtasab, WANLP 2022)
ACL