Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Malay phoneme-based subword news headline generator for low-resource language

IAES International Journal of Artificial Intelligence · Vol. 13 No. 4 (2024) · hlm. 4965–4975

DOI
10.11591/ijai.v13.i4.pp4965-4975
ISSN
2252-8938, 2089-4872
Terbit
2024-12-01
Penerbit
Institute of Advanced Engineering and Science
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

The booming of technology has significantly increased the amount of news articles for readers. The headline of news plays an essential role in attracting readers. Traditionally, crafting the news headline is a manual task at the news desk. The motivation of this paper is to address the issues faced in low resource languages, such as the Malay language. The main contribution of this paper is a new hybrid model based on extractive- and abstractive-based text summarization with the integration of a geographical linguistics model; a Malay phoneme-based subword embedding has been developed to solve the complex morphological issue in the Malay language-based computational linguistic applications. The experiment involves various sequence-to sequence (seq2seq) models to generate the Malay news headlines. Besides that, the out-of-vocabulary (OOV) is assessed in the models. From the experiment, the proposed hybrid text summarization model shows significant improvement over the baseline models above 11.00 in ROUGE-1, 4.00 ROUGE-2, and 11.00 in ROUGE-L. The proposed model can reduce the OOV rate to below 15%.

Kata kunci

Jaringan kolaborasi para penulis

18 penulis · 42 tautan kepenulisan bersama · 24 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Universiti Teknologi Petronas
  • UOW Malaysia KDU College
  • Universiti Tenaga Nasional
  • Telkom University
  • Taylor's College
  • Coventry University
  • Bahauddin Zakariya University
  • Organisasi lain
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Abdul SaboorUniversiti Teknologi Petronas1
Samah AbuSalimUniversiti Teknologi Petronas1
Nordin ZakariaUniversiti Teknologi Petronas1
Aarish MaqsoodBahauddin Zakariya University1
Norehan Binti MokhtarUniversiti Sains Malaysia1
Said Jadid AbdulkadirUniversiti Teknologi Petronas1
Sujata NavaratnamUOW Malaysia KDU College1
Chon-Moy KangUOW Malaysia KDU College1
Wai-Seong CheUOW Malaysia KDU College1
Agileswari K. RamasamyUniversiti Tenaga Nasional1
Nadia M. L. TanUniversiti Tenaga Nasional1
H.K. ChiuUniversiti Tenaga Nasional1
Erwin SusantoTelkom University1
Sony SumaryoTelkom University1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) http://ijai.iaescore.com/index.php/IJAI/oai, pertama di-harvest 8 Nov 2026, terakhir terlihat 16 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Malay phoneme-based subword news headline generator for low-resource language</dc:title>
	<dc:creator>Tsann Phua, Yeong</dc:creator>
	<dc:creator>Hooi Yew, Kwang</dc:creator>
	<dc:creator>Fadzil Hassan, Mohd</dc:creator>
	<dc:creator>Yok Wooi, Matthew Teow</dc:creator>
	<dc:subject xml:lang="en-US">Natural Language Processing</dc:subject>
	<dc:subject xml:lang="en-US">Low-resource language; Malay language; Natural language processing; News headline generator; Subword embedding</dc:subject>
	<dc:description xml:lang="en-US">The booming of technology has significantly increased the amount of news articles for readers. The headline of news plays an essential role in attracting readers. Traditionally, crafting the news headline is a manual task at the news desk. The motivation of this paper is to address the issues faced in low resource languages, such as the Malay language. The main contribution of this paper is a new hybrid model based on extractive- and abstractive-based text summarization with the integration of a geographical linguistics model; a Malay phoneme-based subword embedding has been developed to solve the complex morphological issue in the Malay language-based computational linguistic applications. The experiment involves various sequence-to sequence (seq2seq) models to generate the Malay news headlines. Besides that, the out-of-vocabulary (OOV) is assessed in the models. From the experiment, the proposed hybrid text summarization model shows significant improvement over the baseline models above 11.00 in ROUGE-1, 4.00 ROUGE-2, and 11.00 in ROUGE-L. The proposed model can reduce the OOV rate to below 15%.</dc:description>
	<dc:publisher xml:lang="en-US">Institute of Advanced Engineering and Science</dc:publisher>
	<dc:contributor xml:lang="en-US">Universiti Teknologi PETRONAS</dc:contributor>
	<dc:date>2024-12-01</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US"></dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://ijai.iaescore.com/index.php/IJAI/article/view/24834</dc:identifier>
	<dc:identifier>10.11591/ijai.v13.i4.pp4965-4975</dc:identifier>
	<dc:source xml:lang="en-US">IAES International Journal of Artificial Intelligence (IJ-AI); Vol 13, No 4: December 2024; 4965-4975</dc:source>
	<dc:source>2252-8938</dc:source>
	<dc:source>2089-4872</dc:source>
	<dc:source>10.11591/ijai.v13.i4</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://ijai.iaescore.com/index.php/IJAI/article/view/24834/14259</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2024 Institute of Advanced Engineering and Science</dc:rights>
	<dc:rights xml:lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>