MATSFT: User query-based multilingual abstractive text summarization for low resource Indian languages by fine-tuning mT5
User query-based summarization is a challenging research area of natural language processing. However, the existing approaches struggle to effectively manage the intricate long-distance semantic relationships between user queries and input documents. This paper introduces a user query-based multilin...
Uložené v:
| Vydané v: | Alexandria engineering journal Ročník 127; s. 129 - 142 |
|---|---|
| Hlavní autori: | , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier B.V
01.08.2025
Elsevier |
| Predmet: | |
| ISSN: | 1110-0168 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | User query-based summarization is a challenging research area of natural language processing. However, the existing approaches struggle to effectively manage the intricate long-distance semantic relationships between user queries and input documents. This paper introduces a user query-based multilingual abstractive text summarization approach for the Indian low-resource languages by fine-tuning the multilingual pre-trained text-to-text (mT5) transformer model (MATSFT). The MATSFT employs a co-attention mechanism within a shared encoder–decoder architecture alongside the mT5 model to transfer knowledge across multiple low-resource languages. The Co-attention captures cross-lingual dependencies, which allows the model to understand the relationships and nuances between the different languages. Most multilingual summarization datasets focus on major global languages like English, French, and Spanish. To address the challenges in the LRLs, we created an Indian language dataset, comprising seven LRLs and the English language, by extracting data from the BBC news website. We evaluate the performance of the MATSFT using the ROUGE metric and a language-agnostic target summary evaluation metric. Experimental results show that MATSFT outperforms the monolingual transformer model, pre-trained MTM, mT5 model, NLI model, IndicBART, mBART25, and mBART50 on the IL dataset. The statistical paired t-test indicates that the MATSFT achieves a significant improvement with a p-value of ≤ 0.05 compared to other models.
[Display omitted]
•Query-focused summarization enabling concise, relevant results across complex, distant contexts.•Proposed a MATSFT unified framework for multilingual text summarization.•Proposed the Indian Language (IL) dataset with 7 Indian and English languages.•Proposed LaTSEM metric to evaluate MATSFT model performance.•We fine-tune mT5 for concise, coherent summaries based on user queries. |
|---|---|
| AbstractList | User query-based summarization is a challenging research area of natural language processing. However, the existing approaches struggle to effectively manage the intricate long-distance semantic relationships between user queries and input documents. This paper introduces a user query-based multilingual abstractive text summarization approach for the Indian low-resource languages by fine-tuning the multilingual pre-trained text-to-text (mT5) transformer model (MATSFT). The MATSFT employs a co-attention mechanism within a shared encoder–decoder architecture alongside the mT5 model to transfer knowledge across multiple low-resource languages. The Co-attention captures cross-lingual dependencies, which allows the model to understand the relationships and nuances between the different languages. Most multilingual summarization datasets focus on major global languages like English, French, and Spanish. To address the challenges in the LRLs, we created an Indian language dataset, comprising seven LRLs and the English language, by extracting data from the BBC news website. We evaluate the performance of the MATSFT using the ROUGE metric and a language-agnostic target summary evaluation metric. Experimental results show that MATSFT outperforms the monolingual transformer model, pre-trained MTM, mT5 model, NLI model, IndicBART, mBART25, and mBART50 on the IL dataset. The statistical paired t-test indicates that the MATSFT achieves a significant improvement with a p-value of ≤ 0.05 compared to other models. User query-based summarization is a challenging research area of natural language processing. However, the existing approaches struggle to effectively manage the intricate long-distance semantic relationships between user queries and input documents. This paper introduces a user query-based multilingual abstractive text summarization approach for the Indian low-resource languages by fine-tuning the multilingual pre-trained text-to-text (mT5) transformer model (MATSFT). The MATSFT employs a co-attention mechanism within a shared encoder–decoder architecture alongside the mT5 model to transfer knowledge across multiple low-resource languages. The Co-attention captures cross-lingual dependencies, which allows the model to understand the relationships and nuances between the different languages. Most multilingual summarization datasets focus on major global languages like English, French, and Spanish. To address the challenges in the LRLs, we created an Indian language dataset, comprising seven LRLs and the English language, by extracting data from the BBC news website. We evaluate the performance of the MATSFT using the ROUGE metric and a language-agnostic target summary evaluation metric. Experimental results show that MATSFT outperforms the monolingual transformer model, pre-trained MTM, mT5 model, NLI model, IndicBART, mBART25, and mBART50 on the IL dataset. The statistical paired t-test indicates that the MATSFT achieves a significant improvement with a p-value of ≤ 0.05 compared to other models. [Display omitted] •Query-focused summarization enabling concise, relevant results across complex, distant contexts.•Proposed a MATSFT unified framework for multilingual text summarization.•Proposed the Indian Language (IL) dataset with 7 Indian and English languages.•Proposed LaTSEM metric to evaluate MATSFT model performance.•We fine-tune mT5 for concise, coherent summaries based on user queries. |
| Author | Abdul, Ashu Reddy, V. Dinesh Prasad, M. Krishna Siva Phani, Siginamsetty |
| Author_xml | – sequence: 1 givenname: Siginamsetty orcidid: 0000-0002-9402-8332 surname: Phani fullname: Phani, Siginamsetty email: siginamsettyphani@gmail.com organization: Department of Computer Science and Engineering, SRM University AP, Neerukonda, Managalagiri, 522502, Andhra Pradesh, India – sequence: 2 givenname: Ashu orcidid: 0000-0003-0221-8225 surname: Abdul fullname: Abdul, Ashu email: ashu.a507@gmail.com organization: Department of Computer Science and Engineering, SRM University AP, Neerukonda, Managalagiri, 522502, Andhra Pradesh, India – sequence: 3 givenname: M. Krishna Siva orcidid: 0000-0002-9782-6401 surname: Prasad fullname: Prasad, M. Krishna Siva email: krishnasivaprasad536@gmail.com organization: Department of Computer Science and Engineering, SRM University AP, Neerukonda, Managalagiri, 522502, Andhra Pradesh, India – sequence: 4 givenname: V. Dinesh orcidid: 0000-0003-3945-6171 surname: Reddy fullname: Reddy, V. Dinesh email: dineshvemula@gmail.com organization: Department of Computer Science and Engineering, SRM University AP, Neerukonda, Managalagiri, 522502, Andhra Pradesh, India |
| BookMark | eNp9kMFO3DAQhn2gEhR4AG5-gaS24zjZ9oRQKSuBOLCcrYk9WTnK2q3tANunx8tWHDuXkWbm__TP_5Wc-OCRkCvOas64-jbVgFMtmGhrJmvW8BNyxjlnVVn2p-QypYmVaruVXKkzsn-43jzdbr7T54SR_lkw7qsBElq6W-bsZue3C8wUhpQjmOxekGZ8yzQtux1E9xeyC56OIdI5vNKIKSzRIF1768DTGQ7yLSY67OnoPFZ58QVJd5v2gnwZYU54-a-fk-fbn5ubu-r-8df65vq-Mo1iuZLWGCOQGSGU6a2VCi2CANvJxti2aaC35UapoVess1ypru9Ew9Gg7Uw7NOdkfeTaAJP-HV3xvdcBnP4YhLjVELMzM-p2bAc0CoUUKHnXr_jApTLMclB2aLCw-JFlYkgp4vjJ40wf4teTLvHrQ_yaSV3iL5ofRw2WJ18cRp2MQ1_suYgmFxfuP-p3lfeThg |
| Cites_doi | 10.1016/j.eswa.2023.120302 10.3390/app11219872 10.1016/j.procs.2022.01.182 10.1162/coli_a_00434 10.1016/j.jksuci.2021.04.004 10.1016/j.eswa.2020.113679 10.1109/ACCESS.2021.3129786 10.1109/ACCESS.2021.3052783 10.1016/j.csl.2021.101276 10.18653/v1/D16-1264 10.1016/j.eswa.2024.124567 10.1145/3611306 10.1016/j.knosys.2022.108636 10.1145/3419106 10.1016/j.asoc.2023.110994 10.1016/j.knosys.2024.111447 10.18653/v1/2023.acl-long.843 10.18653/v1/E17-2007 10.1162/coli_a_00425 10.1111/lang.12407 10.1016/j.eswa.2023.123045 |
| ContentType | Journal Article |
| Copyright | 2025 The Author(s) |
| Copyright_xml | – notice: 2025 The Author(s) |
| DBID | 6I. AAFTH AAYXX CITATION DOA |
| DOI | 10.1016/j.aej.2025.04.031 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EndPage | 142 |
| ExternalDocumentID | oai_doaj_org_article_5f5bec6e242e417891b146c0d1a6db3e 10_1016_j_aej_2025_04_031 S1110016825005162 |
| GroupedDBID | --K 0R~ 4.4 457 5VS 6I. AAEDT AAEDW AAFTH AAIKJ AALRI AAXUO AAYWO ABMAC ACGFS ACVFH ADBBV ADCNI ADEZE ADVLN AEUPX AEXQZ AFJKZ AFPUW AFTJW AGHFR AIGII AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ BCNDV EBS EJD FDB GROUPED_DOAJ HZ~ IPNFZ IXB KQ8 M41 O-L O9- OK1 P2P RIG ROL SES SSZ XH2 AAYXX CITATION |
| ID | FETCH-LOGICAL-c360t-4dccc2e0c226c8dd46edea2ad743cd533a8d4dc66b8607d166787231eced7c5b3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001490918100005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1110-0168 |
| IngestDate | Fri Oct 03 12:51:23 EDT 2025 Sat Nov 29 07:40:23 EST 2025 Sat Sep 20 17:14:37 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Co-attention mechanism Shared encoder–decoder Fine-tuning mT5 Multilingual text summarization User query-based summarization |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c360t-4dccc2e0c226c8dd46edea2ad743cd533a8d4dc66b8607d166787231eced7c5b3 |
| ORCID | 0000-0002-9402-8332 0000-0002-9782-6401 0000-0003-0221-8225 0000-0003-3945-6171 |
| OpenAccessLink | https://doaj.org/article/5f5bec6e242e417891b146c0d1a6db3e |
| PageCount | 14 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_5f5bec6e242e417891b146c0d1a6db3e crossref_primary_10_1016_j_aej_2025_04_031 elsevier_sciencedirect_doi_10_1016_j_aej_2025_04_031 |
| PublicationCentury | 2000 |
| PublicationDate | August 2025 2025-08-00 2025-08-01 |
| PublicationDateYYYYMMDD | 2025-08-01 |
| PublicationDate_xml | – month: 08 year: 2025 text: August 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | Alexandria engineering journal |
| PublicationYear | 2025 |
| Publisher | Elsevier B.V Elsevier |
| Publisher_xml | – name: Elsevier B.V – name: Elsevier |
| References | P. Rajpurkar, J. Zhang, K. Lopyrev, P. Liang, Squad: 100, 000+ questions for machine comprehension of text, in: EMNLP, 2016, pp. 2383–2392. Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (b33) 2017; vol. 30 Wahab, Hamid, Subramaniam, Latip, Othman (b18) 2024; 151 Vats, Sharma, Sharma (b12) 2023 Alomari, Idris, Sabri, Alsmadi (b24) 2022; 71 Benedetto, La Quatra, Cagliero, Vassio, Trevisan (b27) 2024; 255 Aharoni, Narayan, Maynez, Herzig, Clark, Lapata (b41) 2023 Mridha, Lima, Nur, Das, Hasan, Kabir (b3) 2021; 9 Laskar, Hoque, Huang (b25) 2022; 48 N. Foroutan, A. Romanou, S. Massonnet, R. Lebret, K. Aberer, Multilingual text summarization on financial documents, in: Proceedings of the 4th Financial Narrative Processing Workshop@ LREC2022, 2022, pp. 53–58. Brugger, türmer, Niklaus (b29) 2023 Tian, Song, Ting, Huang (b34) 2022; 199 Reimers, Gurevych (b32) 2019 J. Li, J. Chen, H. Chen, D. Zhao, R. Yan, Multilingual Generation in Abstractive Summarization: A Comparative Study, in: Proc. 2024 Joint Int. Conf. Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024, 2024, pp. 11827–11837. Ahuir, Hurtado, González, Segarra (b8) 2021; 11 Xue, Constant, Roberts, Kale, Al-Rfou, Siddhant, Barua, Raffel (b9) 2020 D.P. Kingma, J. Ba, Adam: A method for stochastic optimization, in: Published As a Conference Paper at the 3rd International Conference for Learning Representations, 2014. Syed, Gaol, Matsuo (b6) 2021; 9 Şahin (b44) 2022; 48 El-Kassas, Salama, Rafea, Mohamed (b13) 2021; 165 Burchell, Birch, Heafield (b37) 2022 J. Wang, F. Meng, D. Zheng, Y. Liang, Z. Li, J. Qu, J. Zhou, Towards unifying multi-lingual and cross-lingual summarization, in: Proc. of the 61st Annual Meeting of the Association for Computational Linguistics, 2023, pp. 15127–15143. Mutlu, Sezer (b15) 2023; 227 Shi, Keneshloo, Ramakrishnan, Reddy (b19) 2021; 2 French, in: Proceedings of the Thirteenth Language Resources and Evaluation Conf., 2022, pp. 6654–6661. Srivastava, Singh, Rana, Kumar (b14) 2022; 246 Deng, Zhang, Xu, Shen, Lam (b4) 2023 Abualigah, Bashabsheh, Alabool, Shehab (b5) 2020 Vo, Vo, Le (b17) 2024; 245 El-Kassas, Salama, Rafea, Mohamed (b2) 2021; 165 Berthele (b11) 2021; 71 Liu, Sun, Yu, Wang, Peng, Hou, Guo, Wang, Liu (b26) 2024; 287 Alomari, Idris, Sabri, Alsmadi (b21) 2022; 71 Huang, Zhou, Zaïane, Mou, Li (b35) 2022; vol. 36 Savelieva, Au. Yeung, Ramani (b23) 2020 - Hasan, Bhattacharjee, Islam, Samin, Li, Kang, Rahman, Shahriyar (b10) 2021 Scialom, Dray, Lamprier, Piwowarski, Staiano (b30) 2020 N. Schluter, The limits of automatic summarisation according to rouge, in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, 2017, pp. 41–45. Tomer, Kumar (b16) 2022; 34 Srivastava, Hinton, Krizhevsky, Sutskever, Salakhutdinov (b40) 2014; 15 Kovačević, Kečo (b22) 2021 C.M.B. Dione, A. Lo, E.M. Nguer, S. Ba, Low-resource Neural Machine Translation: Benchmarking State-of-the-art Transformer for Wolof Dabre, Shrotriya, Kunchukuttan, Puduppully, Khapra, Kumar (b42) 2022 H.Q. To, K. Van Nguyen, N.L.T. Nguyen, A.G.T. Nguyen, Monolingual vs multilingual BERTology for Vietnamese extractive multi-document summarization, in: Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation, 2021, pp. 692–699. Tan, Wan, Xiao (b20) 2017; vol. 1 Mridha (10.1016/j.aej.2025.04.031_b3) 2021; 9 Brugger (10.1016/j.aej.2025.04.031_b29) 2023 10.1016/j.aej.2025.04.031_b39 Tan (10.1016/j.aej.2025.04.031_b20) 2017; vol. 1 10.1016/j.aej.2025.04.031_b38 El-Kassas (10.1016/j.aej.2025.04.031_b2) 2021; 165 Abualigah (10.1016/j.aej.2025.04.031_b5) 2020 Benedetto (10.1016/j.aej.2025.04.031_b27) 2024; 255 El-Kassas (10.1016/j.aej.2025.04.031_b13) 2021; 165 Aharoni (10.1016/j.aej.2025.04.031_b41) 2023 Scialom (10.1016/j.aej.2025.04.031_b30) 2020 Berthele (10.1016/j.aej.2025.04.031_b11) 2021; 71 Reimers (10.1016/j.aej.2025.04.031_b32) 2019 Syed (10.1016/j.aej.2025.04.031_b6) 2021; 9 10.1016/j.aej.2025.04.031_b1 Kovačević (10.1016/j.aej.2025.04.031_b22) 2021 Deng (10.1016/j.aej.2025.04.031_b4) 2023 10.1016/j.aej.2025.04.031_b7 10.1016/j.aej.2025.04.031_b31 Xue (10.1016/j.aej.2025.04.031_b9) 2020 Liu (10.1016/j.aej.2025.04.031_b26) 2024; 287 Tomer (10.1016/j.aej.2025.04.031_b16) 2022; 34 10.1016/j.aej.2025.04.031_b36 10.1016/j.aej.2025.04.031_b28 Vats (10.1016/j.aej.2025.04.031_b12) 2023 Wahab (10.1016/j.aej.2025.04.031_b18) 2024; 151 Tian (10.1016/j.aej.2025.04.031_b34) 2022; 199 Srivastava (10.1016/j.aej.2025.04.031_b14) 2022; 246 Dabre (10.1016/j.aej.2025.04.031_b42) 2022 Huang (10.1016/j.aej.2025.04.031_b35) 2022; vol. 36 Srivastava (10.1016/j.aej.2025.04.031_b40) 2014; 15 Alomari (10.1016/j.aej.2025.04.031_b24) 2022; 71 Savelieva (10.1016/j.aej.2025.04.031_b23) 2020 Burchell (10.1016/j.aej.2025.04.031_b37) 2022 Shi (10.1016/j.aej.2025.04.031_b19) 2021; 2 Ahuir (10.1016/j.aej.2025.04.031_b8) 2021; 11 Laskar (10.1016/j.aej.2025.04.031_b25) 2022; 48 10.1016/j.aej.2025.04.031_b43 Vaswani (10.1016/j.aej.2025.04.031_b33) 2017; vol. 30 Mutlu (10.1016/j.aej.2025.04.031_b15) 2023; 227 Vo (10.1016/j.aej.2025.04.031_b17) 2024; 245 Hasan (10.1016/j.aej.2025.04.031_b10) 2021 Şahin (10.1016/j.aej.2025.04.031_b44) 2022; 48 Alomari (10.1016/j.aej.2025.04.031_b21) 2022; 71 |
| References_xml | – volume: 227 year: 2023 ident: b15 article-title: Enhanced sentence representation for extractive text summarization: Investigating the syntactic and semantic features and their contribution to sentence scoring publication-title: Expert Syst. Appl. – reference: N. Foroutan, A. Romanou, S. Massonnet, R. Lebret, K. Aberer, Multilingual text summarization on financial documents, in: Proceedings of the 4th Financial Narrative Processing Workshop@ LREC2022, 2022, pp. 53–58. – volume: 199 start-page: 1438 year: 2022 end-page: 1443 ident: b34 article-title: A french-to-english machine translation model using transformer network publication-title: Procedia Comput. Sci. – volume: vol. 36 start-page: 10776 year: 2022 end-page: 10784 ident: b35 article-title: Non-autoregressive translation with layer-wise prediction and deep supervision publication-title: Proceedings of the AAAI Conf. on Artificial Intelligence – volume: 246 year: 2022 ident: b14 article-title: A topic modeled unsupervised approach to single document extractive text summarization publication-title: Knowl.-Based Syst. – volume: 151 year: 2024 ident: b18 article-title: Decomposition–based multi-objective differential evolution for extractive multi-document automatic text summarization publication-title: Appl. Soft Comput. – volume: 9 start-page: 13248 year: 2021 end-page: 13265 ident: b6 article-title: A survey of the state-of-the-art models in neural abstractive text summarization publication-title: IEEE Access – start-page: 4693 year: 2021 end-page: 4703 ident: b10 article-title: XL-sum: Large-scale multilingual abstractive summarization for 44 languages publication-title: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 – volume: 48 start-page: 279 year: 2022 end-page: 320 ident: b25 article-title: Domain adaptation with pre-trained transformers for query-focused abstractive text summarization publication-title: Comput. Linguist. – volume: 34 start-page: 6057 year: 2022 end-page: 6065 ident: b16 article-title: Multi-document extractive text summarization based on firefly algorithm publication-title: J. King Saud Univ.- Comput. Inf. Sci. – reference: French, in: Proceedings of the Thirteenth Language Resources and Evaluation Conf., 2022, pp. 6654–6661. – volume: 165 year: 2021 ident: b2 article-title: Automatic text summarization: A comprehensive survey publication-title: Expert Syst. Appl. – volume: 11 start-page: 9872 year: 2021 ident: b8 article-title: Nasca and nases: Two monolingual pre-trained models for abstractive summarization in catalan and spanish publication-title: Appl. Sci. – start-page: 11934 year: 2020 ident: b9 article-title: mT5: A massively multilingual pre-trained text-to-text transformer publication-title: Comput. Lang. – reference: P. Rajpurkar, J. Zhang, K. Lopyrev, P. Liang, Squad: 100, 000+ questions for machine comprehension of text, in: EMNLP, 2016, pp. 2383–2392. – volume: 255 year: 2024 ident: b27 article-title: TASP: Topic-based abstractive summarization of facebook text posts publication-title: Expert Syst. Appl. – year: 2023 ident: b12 article-title: HKG: A novel approach for low resource indic languages to automatic knowledge graph construction publication-title: ACM Trans. Asian Low- Resour. Lang. Inf. Process. – volume: 71 year: 2022 ident: b21 article-title: Deep reinforcement and transfer learning for abstractive text summarization: A review publication-title: Comput. Speech Lang. – volume: 9 start-page: 156043 year: 2021 end-page: 1–56070 ident: b3 article-title: A survey of automatic text summarization: Progress, process and challenges publication-title: IEEE Access – reference: J. Li, J. Chen, H. Chen, D. Zhao, R. Yan, Multilingual Generation in Abstractive Summarization: A Comparative Study, in: Proc. 2024 Joint Int. Conf. Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024, 2024, pp. 11827–11837. – volume: 245 year: 2024 ident: b17 article-title: Interpretable extractive text summarization with meta-learning and BI-LSTM: A study of meta learning and explainability techniques publication-title: Expert Syst. Appl. – reference: - – year: 2022 ident: b37 article-title: Exploring diversity in back translation for low-resource machine translation publication-title: Comput. Lang. – volume: 71 year: 2022 ident: b24 article-title: Deep reinforcement and transfer learning for abstractive text summarization: A review publication-title: Comput. Speech Lang. – volume: 165 year: 2021 ident: b13 article-title: Automatic text summarization: A comprehensive survey publication-title: Expert Syst. Appl. – year: 2020 ident: b23 article-title: Abstractive summarization of spoken and written instructions with bert publication-title: Comput. Lang. – volume: 71 start-page: 80 year: 2021 end-page: 120 ident: b11 article-title: The extraordinary ordinary: Re-engineering multilingualism as a natural category publication-title: Lang. Learn. – reference: N. Schluter, The limits of automatic summarisation according to rouge, in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, 2017, pp. 41–45. – volume: 15 start-page: 1929 year: 2014 end-page: 1958 ident: b40 article-title: Dropout: a simple way to prevent neural networks from overfitting publication-title: J. Mach. Learn. Res. – reference: D.P. Kingma, J. Ba, Adam: A method for stochastic optimization, in: Published As a Conference Paper at the 3rd International Conference for Learning Representations, 2014. – year: 2020 ident: b30 article-title: MLSUM: The multilingual summarization corpus publication-title: Proc. of the 2020 Conf. on Empirical Methods in Natural Language Processing – year: 2019 ident: b32 article-title: Sentence-bert: Sentence embeddings using siamese bert-networks publication-title: Proc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing – start-page: 3562 year: 2023 end-page: 3591 ident: b41 article-title: mface: Multilingual Summarization with Factual Consistency Evaluation – volume: 48 start-page: 5 year: 2022 end-page: 42 ident: b44 article-title: To augment or not to augment? A comparative study on text augmentation techniques for low-resource NLP publication-title: Comput. Linguist. – year: 2023 ident: b29 article-title: MultiLegalSBD: A multilingual legal sentence boundary detection dataset publication-title: Comput. Lang. – reference: J. Wang, F. Meng, D. Zheng, Y. Liang, Z. Li, J. Qu, J. Zhou, Towards unifying multi-lingual and cross-lingual summarization, in: Proc. of the 61st Annual Meeting of the Association for Computational Linguistics, 2023, pp. 15127–15143. – volume: 287 year: 2024 ident: b26 article-title: Automatic text summarization method based on improved TextRank algorithm and K-means clustering publication-title: Knowl.-Based Syst. – volume: 2 start-page: 1 year: 2021 end-page: 37 ident: b19 article-title: Neural abstractive text summarization with sequence-to-sequence models. publication-title: ACM Trans. Data Sci. – start-page: 1 year: 2020 end-page: 15 ident: b5 article-title: Text summarization: a brief review publication-title: Recent Advances in NLP: The Case of Arabic Language – start-page: 281 year: 2021 end-page: 293 ident: b22 article-title: Bidirectional LSTM networks for abstractive text summarization publication-title: International Symposium on Innovative and Interdisciplinary Applications of Advanced Technologies – reference: C.M.B. Dione, A. Lo, E.M. Nguer, S. Ba, Low-resource Neural Machine Translation: Benchmarking State-of-the-art Transformer for Wolof – volume: vol. 30 year: 2017 ident: b33 article-title: Attention is all you need publication-title: Advances in neural information processing systems – start-page: 1849 year: 2022 end-page: 1863 ident: b42 article-title: IndicBART: A Pre-Trained Model for Indic Natural Language Generation – volume: vol. 1 start-page: 1171 year: 2017 end-page: 1181 ident: b20 article-title: Abstractive document summarization with a graph-based attentional neural model publication-title: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics – year: 2023 ident: b4 article-title: Nonfactoid question answering as query-focused summarization with graph-enhanced multihop inference publication-title: IEEE Trans. Neural Netw. Learn. Syst. – reference: H.Q. To, K. Van Nguyen, N.L.T. Nguyen, A.G.T. Nguyen, Monolingual vs multilingual BERTology for Vietnamese extractive multi-document summarization, in: Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation, 2021, pp. 692–699. – year: 2019 ident: 10.1016/j.aej.2025.04.031_b32 article-title: Sentence-bert: Sentence embeddings using siamese bert-networks – volume: 227 year: 2023 ident: 10.1016/j.aej.2025.04.031_b15 article-title: Enhanced sentence representation for extractive text summarization: Investigating the syntactic and semantic features and their contribution to sentence scoring publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2023.120302 – start-page: 1 year: 2020 ident: 10.1016/j.aej.2025.04.031_b5 article-title: Text summarization: a brief review – year: 2020 ident: 10.1016/j.aej.2025.04.031_b30 article-title: MLSUM: The multilingual summarization corpus – volume: 11 start-page: 9872 issue: 21 year: 2021 ident: 10.1016/j.aej.2025.04.031_b8 article-title: Nasca and nases: Two monolingual pre-trained models for abstractive summarization in catalan and spanish publication-title: Appl. Sci. doi: 10.3390/app11219872 – volume: 199 start-page: 1438 year: 2022 ident: 10.1016/j.aej.2025.04.031_b34 article-title: A french-to-english machine translation model using transformer network publication-title: Procedia Comput. Sci. doi: 10.1016/j.procs.2022.01.182 – year: 2023 ident: 10.1016/j.aej.2025.04.031_b4 article-title: Nonfactoid question answering as query-focused summarization with graph-enhanced multihop inference publication-title: IEEE Trans. Neural Netw. Learn. Syst. – year: 2020 ident: 10.1016/j.aej.2025.04.031_b23 article-title: Abstractive summarization of spoken and written instructions with bert publication-title: Comput. Lang. – start-page: 11934 year: 2020 ident: 10.1016/j.aej.2025.04.031_b9 article-title: mT5: A massively multilingual pre-trained text-to-text transformer publication-title: Comput. Lang. – start-page: 3562 year: 2023 ident: 10.1016/j.aej.2025.04.031_b41 – volume: 48 start-page: 279 issue: 2 year: 2022 ident: 10.1016/j.aej.2025.04.031_b25 article-title: Domain adaptation with pre-trained transformers for query-focused abstractive text summarization publication-title: Comput. Linguist. doi: 10.1162/coli_a_00434 – volume: vol. 30 year: 2017 ident: 10.1016/j.aej.2025.04.031_b33 article-title: Attention is all you need – volume: 34 start-page: 6057 issue: 8 year: 2022 ident: 10.1016/j.aej.2025.04.031_b16 article-title: Multi-document extractive text summarization based on firefly algorithm publication-title: J. King Saud Univ.- Comput. Inf. Sci. doi: 10.1016/j.jksuci.2021.04.004 – year: 2022 ident: 10.1016/j.aej.2025.04.031_b37 article-title: Exploring diversity in back translation for low-resource machine translation publication-title: Comput. Lang. – ident: 10.1016/j.aej.2025.04.031_b39 – start-page: 281 year: 2021 ident: 10.1016/j.aej.2025.04.031_b22 article-title: Bidirectional LSTM networks for abstractive text summarization – ident: 10.1016/j.aej.2025.04.031_b31 – volume: 15 start-page: 1929 issue: 1 year: 2014 ident: 10.1016/j.aej.2025.04.031_b40 article-title: Dropout: a simple way to prevent neural networks from overfitting publication-title: J. Mach. Learn. Res. – volume: vol. 36 start-page: 10776 year: 2022 ident: 10.1016/j.aej.2025.04.031_b35 article-title: Non-autoregressive translation with layer-wise prediction and deep supervision – start-page: 4693 year: 2021 ident: 10.1016/j.aej.2025.04.031_b10 article-title: XL-sum: Large-scale multilingual abstractive summarization for 44 languages – volume: vol. 1 start-page: 1171 year: 2017 ident: 10.1016/j.aej.2025.04.031_b20 article-title: Abstractive document summarization with a graph-based attentional neural model – volume: 165 year: 2021 ident: 10.1016/j.aej.2025.04.031_b13 article-title: Automatic text summarization: A comprehensive survey publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2020.113679 – volume: 9 start-page: 156043 year: 2021 ident: 10.1016/j.aej.2025.04.031_b3 article-title: A survey of automatic text summarization: Progress, process and challenges publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3129786 – volume: 9 start-page: 13248 year: 2021 ident: 10.1016/j.aej.2025.04.031_b6 article-title: A survey of the state-of-the-art models in neural abstractive text summarization publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3052783 – volume: 71 year: 2022 ident: 10.1016/j.aej.2025.04.031_b24 article-title: Deep reinforcement and transfer learning for abstractive text summarization: A review publication-title: Comput. Speech Lang. doi: 10.1016/j.csl.2021.101276 – year: 2023 ident: 10.1016/j.aej.2025.04.031_b29 article-title: MultiLegalSBD: A multilingual legal sentence boundary detection dataset publication-title: Comput. Lang. – start-page: 1849 year: 2022 ident: 10.1016/j.aej.2025.04.031_b42 – volume: 165 year: 2021 ident: 10.1016/j.aej.2025.04.031_b2 article-title: Automatic text summarization: A comprehensive survey publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2020.113679 – ident: 10.1016/j.aej.2025.04.031_b7 – volume: 71 year: 2022 ident: 10.1016/j.aej.2025.04.031_b21 article-title: Deep reinforcement and transfer learning for abstractive text summarization: A review publication-title: Comput. Speech Lang. doi: 10.1016/j.csl.2021.101276 – ident: 10.1016/j.aej.2025.04.031_b1 doi: 10.18653/v1/D16-1264 – volume: 255 year: 2024 ident: 10.1016/j.aej.2025.04.031_b27 article-title: TASP: Topic-based abstractive summarization of facebook text posts publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2024.124567 – year: 2023 ident: 10.1016/j.aej.2025.04.031_b12 article-title: HKG: A novel approach for low resource indic languages to automatic knowledge graph construction publication-title: ACM Trans. Asian Low- Resour. Lang. Inf. Process. doi: 10.1145/3611306 – volume: 246 year: 2022 ident: 10.1016/j.aej.2025.04.031_b14 article-title: A topic modeled unsupervised approach to single document extractive text summarization publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2022.108636 – volume: 2 start-page: 1 issue: 1 year: 2021 ident: 10.1016/j.aej.2025.04.031_b19 article-title: Neural abstractive text summarization with sequence-to-sequence models. publication-title: ACM Trans. Data Sci. doi: 10.1145/3419106 – ident: 10.1016/j.aej.2025.04.031_b28 – volume: 151 year: 2024 ident: 10.1016/j.aej.2025.04.031_b18 article-title: Decomposition–based multi-objective differential evolution for extractive multi-document automatic text summarization publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2023.110994 – volume: 287 year: 2024 ident: 10.1016/j.aej.2025.04.031_b26 article-title: Automatic text summarization method based on improved TextRank algorithm and K-means clustering publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2024.111447 – ident: 10.1016/j.aej.2025.04.031_b43 doi: 10.18653/v1/2023.acl-long.843 – ident: 10.1016/j.aej.2025.04.031_b38 doi: 10.18653/v1/E17-2007 – volume: 48 start-page: 5 issue: 1 year: 2022 ident: 10.1016/j.aej.2025.04.031_b44 article-title: To augment or not to augment? A comparative study on text augmentation techniques for low-resource NLP publication-title: Comput. Linguist. doi: 10.1162/coli_a_00425 – volume: 71 start-page: 80 issue: S1 year: 2021 ident: 10.1016/j.aej.2025.04.031_b11 article-title: The extraordinary ordinary: Re-engineering multilingualism as a natural category publication-title: Lang. Learn. doi: 10.1111/lang.12407 – volume: 245 year: 2024 ident: 10.1016/j.aej.2025.04.031_b17 article-title: Interpretable extractive text summarization with meta-learning and BI-LSTM: A study of meta learning and explainability techniques publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2023.123045 – ident: 10.1016/j.aej.2025.04.031_b36 |
| SSID | ssj0000579496 |
| Score | 2.3477204 |
| Snippet | User query-based summarization is a challenging research area of natural language processing. However, the existing approaches struggle to effectively manage... |
| SourceID | doaj crossref elsevier |
| SourceType | Open Website Index Database Publisher |
| StartPage | 129 |
| SubjectTerms | Co-attention mechanism Fine-tuning mT5 Multilingual text summarization Shared encoder–decoder User query-based summarization |
| Title | MATSFT: User query-based multilingual abstractive text summarization for low resource Indian languages by fine-tuning mT5 |
| URI | https://dx.doi.org/10.1016/j.aej.2025.04.031 https://doaj.org/article/5f5bec6e242e417891b146c0d1a6db3e |
| Volume | 127 |
| WOSCitedRecordID | wos001490918100005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals issn: 1110-0168 databaseCode: DOA dateStart: 20100101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.doaj.org/ omitProxy: false ssIdentifier: ssj0000579496 providerName: Directory of Open Access Journals |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3NS8MwFA8yPOhB_MT5RQ6ehGLbpGnnbYpDDw7BDnYLSV4KG7pJtyn7731JW6kH8eK1JO-V15e8X15ffo-QS5akDBDm40rrsYAnSRZoYeNAGIBeHIlQh8o3m0iHw2w87j23Wn25mrCKHrgy3HVSJKgGp_PY8ijNepHGxW1CiJQAzazbfRH1tA5TFas3-plvzoVr2VVeiaz5pemLu5Sd4tkwTjzNKYt-BCXP3d-KTa14M9glOzVQpP3qBffIhp3tk-0WfeABWT_185dBfkNH6EcUN_hyHbioBNSXCbqL5isUobRLZ_h9jbo6D1pdWKsvYFJErfR1_knLOpFPH2fOZ2iTyVxQvaYFag2WK5dEoW95ckhGg_v87iGoWykEholwGXAwxsQ2NIi2TAbAhQWrYgUIIAwg5FMZ4BghdCbCFCKBMSxF6GeNhdQkmh2Rzmw-s8eExsxEmXKM41DwFJQqBCsKjVM4ntWAdclVY0v5XjFmyKaUbCrR8NIZXoZcouG75NZZ-3ugI7v2D9AFZO0C8i8X6BLefCtZ44YKD6Coye-6T_5D9ynZciKrksAz0lmWK3tONs3HcrIoL7xTfgHZpuZU |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=MATSFT%3A+User+query-based+multilingual+abstractive+text+summarization+for+low+resource+Indian+languages+by+fine-tuning+mT5&rft.jtitle=Alexandria+engineering+journal&rft.au=Siginamsetty+Phani&rft.au=Ashu+Abdul&rft.au=M.+Krishna+Siva+Prasad&rft.au=V.+Dinesh+Reddy&rft.date=2025-08-01&rft.pub=Elsevier&rft.issn=1110-0168&rft.volume=127&rft.spage=129&rft.epage=142&rft_id=info:doi/10.1016%2Fj.aej.2025.04.031&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_5f5bec6e242e417891b146c0d1a6db3e |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1110-0168&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1110-0168&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1110-0168&client=summon |