Answer Agnostic Question Generation in Bangla Language Article Swipe
Abdur Rahman Fahad
,
Nazme Al Nahian
,
Md Ahanaf Islam
,
Rashedur M. Rahman
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.1007/s44227-023-00018-5
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.1007/s44227-023-00018-5
Question generation (QG) from a given context paragraph is a demanding task in natural language processing for its practical applications and prospects in various fields. Several studies have been conducted on QG in high-resource languages like English, however, very few have been done on resource-poor languages like Arabic and Bangla. In this work, we propose a finetuning method for QG that uses pre-trained transformer-based language models to generate questions from a given context paragraph in Bangla. Our approach is based on the idea that a transformer-based language model can be used to learn the relationships between words and phrases in a context paragraph which allows the models to generate questions that are both relevant and grammatically correct. We finetuned three different transformer models: (1) BanglaT5, (2) mT5-base, (3) BanglaGPT2, and demonstrated their capabilities using two different data formatting techniques: (1) AQL—All Question Per Line, (2) OQL—One Question Per Line, making it a total of six different variations of QG models. For each of these variants, six different decoding algorithms: (1) Greedy search, (2) Beam search, (3) Random Sampling, (4) Top K sampling, (5) Top- p Sampling, 6) a combination of Top K and Top-p Sampling were used to generate questions from the test dataset. For evaluation of the quality of questions generated using different models and decoding techniques, we also fine-tuned another transformer model BanglaBert on two custom datasets of our own and created two question classifier (QC) models that check the relevancy and Grammatical correctness of the questions generated by our QG models. The QC models showed test accuracy of 88.54% and 95.76% in the case of correctness and relevancy checks, respectively. Our results show that among all the variants of the QG, the mT5 OQL approach and beam decoding algorithm outperformed all the other ones in terms of relevancy (77%) and correctness (96%) with 36.60 Bleu_4, 48.98 METEOR, and 63.38 ROUGE-L scores.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1007/s44227-023-00018-5
- https://link.springer.com/content/pdf/10.1007/s44227-023-00018-5.pdf
- OA Status
- gold
- Cited By
- 4
- References
- 26
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4390542472
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4390542472Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1007/s44227-023-00018-5Digital Object Identifier
- Title
-
Answer Agnostic Question Generation in Bangla LanguageWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-01-03Full publication date if available
- Authors
-
Abdur Rahman Fahad, Nazme Al Nahian, Md Ahanaf Islam, Rashedur M. RahmanList of authors in order
- Landing page
-
https://doi.org/10.1007/s44227-023-00018-5Publisher landing page
- PDF URL
-
https://link.springer.com/content/pdf/10.1007/s44227-023-00018-5.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://link.springer.com/content/pdf/10.1007/s44227-023-00018-5.pdfDirect OA link when available
- Concepts
-
Computer science, Paragraph, Natural language processing, Artificial intelligence, Transformer, Language model, Bengali, Beam search, Programming language, Search algorithm, World Wide Web, Quantum mechanics, Physics, VoltageTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
4Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 2, 2024: 2Per-year citation counts (last 5 years)
- References (count)
-
26Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4390542472 |
|---|---|
| doi | https://doi.org/10.1007/s44227-023-00018-5 |
| ids.doi | https://doi.org/10.1007/s44227-023-00018-5 |
| ids.openalex | https://openalex.org/W4390542472 |
| fwci | 2.5551142 |
| type | article |
| title | Answer Agnostic Question Generation in Bangla Language |
| biblio.issue | 1 |
| biblio.volume | 12 |
| biblio.last_page | 107 |
| biblio.first_page | 82 |
| topics[0].id | https://openalex.org/T10028 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9998999834060669 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Topic Modeling |
| topics[1].id | https://openalex.org/T10181 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9998000264167786 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Natural Language Processing Techniques |
| topics[2].id | https://openalex.org/T11714 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.989799976348877 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Multimodal Machine Learning Applications |
| is_xpac | False |
| apc_list.value | 350 |
| apc_list.currency | EUR |
| apc_list.value_usd | 377 |
| apc_paid.value | 350 |
| apc_paid.currency | EUR |
| apc_paid.value_usd | 377 |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8440283536911011 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C2777206241 |
| concepts[1].level | 2 |
| concepts[1].score | 0.8042833209037781 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q194431 |
| concepts[1].display_name | Paragraph |
| concepts[2].id | https://openalex.org/C204321447 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6121803522109985 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[2].display_name | Natural language processing |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.6003281474113464 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C66322947 |
| concepts[4].level | 3 |
| concepts[4].score | 0.54776930809021 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[4].display_name | Transformer |
| concepts[5].id | https://openalex.org/C137293760 |
| concepts[5].level | 2 |
| concepts[5].score | 0.47517696022987366 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q3621696 |
| concepts[5].display_name | Language model |
| concepts[6].id | https://openalex.org/C19235068 |
| concepts[6].level | 2 |
| concepts[6].score | 0.46340063214302063 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q9610 |
| concepts[6].display_name | Bengali |
| concepts[7].id | https://openalex.org/C19889080 |
| concepts[7].level | 3 |
| concepts[7].score | 0.4202459156513214 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2835852 |
| concepts[7].display_name | Beam search |
| concepts[8].id | https://openalex.org/C199360897 |
| concepts[8].level | 1 |
| concepts[8].score | 0.24698075652122498 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[8].display_name | Programming language |
| concepts[9].id | https://openalex.org/C125583679 |
| concepts[9].level | 2 |
| concepts[9].score | 0.1415826380252838 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q755673 |
| concepts[9].display_name | Search algorithm |
| concepts[10].id | https://openalex.org/C136764020 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0833246111869812 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q466 |
| concepts[10].display_name | World Wide Web |
| concepts[11].id | https://openalex.org/C62520636 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[11].display_name | Quantum mechanics |
| concepts[12].id | https://openalex.org/C121332964 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[12].display_name | Physics |
| concepts[13].id | https://openalex.org/C165801399 |
| concepts[13].level | 2 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[13].display_name | Voltage |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8440283536911011 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/paragraph |
| keywords[1].score | 0.8042833209037781 |
| keywords[1].display_name | Paragraph |
| keywords[2].id | https://openalex.org/keywords/natural-language-processing |
| keywords[2].score | 0.6121803522109985 |
| keywords[2].display_name | Natural language processing |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.6003281474113464 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/transformer |
| keywords[4].score | 0.54776930809021 |
| keywords[4].display_name | Transformer |
| keywords[5].id | https://openalex.org/keywords/language-model |
| keywords[5].score | 0.47517696022987366 |
| keywords[5].display_name | Language model |
| keywords[6].id | https://openalex.org/keywords/bengali |
| keywords[6].score | 0.46340063214302063 |
| keywords[6].display_name | Bengali |
| keywords[7].id | https://openalex.org/keywords/beam-search |
| keywords[7].score | 0.4202459156513214 |
| keywords[7].display_name | Beam search |
| keywords[8].id | https://openalex.org/keywords/programming-language |
| keywords[8].score | 0.24698075652122498 |
| keywords[8].display_name | Programming language |
| keywords[9].id | https://openalex.org/keywords/search-algorithm |
| keywords[9].score | 0.1415826380252838 |
| keywords[9].display_name | Search algorithm |
| keywords[10].id | https://openalex.org/keywords/world-wide-web |
| keywords[10].score | 0.0833246111869812 |
| keywords[10].display_name | World Wide Web |
| language | en |
| locations[0].id | doi:10.1007/s44227-023-00018-5 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S2764679164 |
| locations[0].source.issn | 2211-7938, 2211-7946 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2211-7938 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | True |
| locations[0].source.display_name | The International journal of networked and distributed computing |
| locations[0].source.host_organization | https://openalex.org/P4310319965 |
| locations[0].source.host_organization_name | Springer Nature |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310319965 |
| locations[0].source.host_organization_lineage_names | Springer Nature |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://link.springer.com/content/pdf/10.1007/s44227-023-00018-5.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | International Journal of Networked and Distributed Computing |
| locations[0].landing_page_url | https://doi.org/10.1007/s44227-023-00018-5 |
| indexed_in | crossref, doaj |
| authorships[0].author.id | https://openalex.org/A5041774547 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Abdur Rahman Fahad |
| authorships[0].countries | BD |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I157386601 |
| authorships[0].affiliations[0].raw_affiliation_string | Department of Electrical and Computer Engineering, North South University, Dhaka, 1229, Bangladesh |
| authorships[0].institutions[0].id | https://openalex.org/I157386601 |
| authorships[0].institutions[0].ror | https://ror.org/05wdbfp45 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I157386601 |
| authorships[0].institutions[0].country_code | BD |
| authorships[0].institutions[0].display_name | North South University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Abdur Rahman Fahad |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Department of Electrical and Computer Engineering, North South University, Dhaka, 1229, Bangladesh |
| authorships[1].author.id | https://openalex.org/A5093645285 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Nazme Al Nahian |
| authorships[1].countries | BD |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I157386601 |
| authorships[1].affiliations[0].raw_affiliation_string | Department of Electrical and Computer Engineering, North South University, Dhaka, 1229, Bangladesh |
| authorships[1].institutions[0].id | https://openalex.org/I157386601 |
| authorships[1].institutions[0].ror | https://ror.org/05wdbfp45 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I157386601 |
| authorships[1].institutions[0].country_code | BD |
| authorships[1].institutions[0].display_name | North South University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Nazme Al Nahian |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Department of Electrical and Computer Engineering, North South University, Dhaka, 1229, Bangladesh |
| authorships[2].author.id | https://openalex.org/A5111105585 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Md Ahanaf Islam |
| authorships[2].countries | BD |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I157386601 |
| authorships[2].affiliations[0].raw_affiliation_string | Department of Electrical and Computer Engineering, North South University, Dhaka, 1229, Bangladesh |
| authorships[2].institutions[0].id | https://openalex.org/I157386601 |
| authorships[2].institutions[0].ror | https://ror.org/05wdbfp45 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I157386601 |
| authorships[2].institutions[0].country_code | BD |
| authorships[2].institutions[0].display_name | North South University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Md Ahanaf Islam |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Department of Electrical and Computer Engineering, North South University, Dhaka, 1229, Bangladesh |
| authorships[3].author.id | https://openalex.org/A5071303493 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-4514-6279 |
| authorships[3].author.display_name | Rashedur M. Rahman |
| authorships[3].countries | BD |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I157386601 |
| authorships[3].affiliations[0].raw_affiliation_string | Department of Electrical and Computer Engineering, North South University, Dhaka, 1229, Bangladesh |
| authorships[3].institutions[0].id | https://openalex.org/I157386601 |
| authorships[3].institutions[0].ror | https://ror.org/05wdbfp45 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I157386601 |
| authorships[3].institutions[0].country_code | BD |
| authorships[3].institutions[0].display_name | North South University |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Rashedur M. Rahman |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Department of Electrical and Computer Engineering, North South University, Dhaka, 1229, Bangladesh |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://link.springer.com/content/pdf/10.1007/s44227-023-00018-5.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Answer Agnostic Question Generation in Bangla Language |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10028 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9998999834060669 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Topic Modeling |
| related_works | https://openalex.org/W4288365749, https://openalex.org/W2936497627, https://openalex.org/W3013624417, https://openalex.org/W4287826556, https://openalex.org/W3098382480, https://openalex.org/W4287598411, https://openalex.org/W3094871513, https://openalex.org/W3100913109, https://openalex.org/W3198458223, https://openalex.org/W3126642501 |
| cited_by_count | 4 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 2 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 2 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1007/s44227-023-00018-5 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S2764679164 |
| best_oa_location.source.issn | 2211-7938, 2211-7946 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2211-7938 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | True |
| best_oa_location.source.display_name | The International journal of networked and distributed computing |
| best_oa_location.source.host_organization | https://openalex.org/P4310319965 |
| best_oa_location.source.host_organization_name | Springer Nature |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310319965 |
| best_oa_location.source.host_organization_lineage_names | Springer Nature |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://link.springer.com/content/pdf/10.1007/s44227-023-00018-5.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | International Journal of Networked and Distributed Computing |
| best_oa_location.landing_page_url | https://doi.org/10.1007/s44227-023-00018-5 |
| primary_location.id | doi:10.1007/s44227-023-00018-5 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S2764679164 |
| primary_location.source.issn | 2211-7938, 2211-7946 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2211-7938 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | True |
| primary_location.source.display_name | The International journal of networked and distributed computing |
| primary_location.source.host_organization | https://openalex.org/P4310319965 |
| primary_location.source.host_organization_name | Springer Nature |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310319965 |
| primary_location.source.host_organization_lineage_names | Springer Nature |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://link.springer.com/content/pdf/10.1007/s44227-023-00018-5.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | International Journal of Networked and Distributed Computing |
| primary_location.landing_page_url | https://doi.org/10.1007/s44227-023-00018-5 |
| publication_date | 2024-01-03 |
| publication_year | 2024 |
| referenced_works | https://openalex.org/W2989613245, https://openalex.org/W4281679314, https://openalex.org/W4382318308, https://openalex.org/W4285306484, https://openalex.org/W6601861260, https://openalex.org/W3003611599, https://openalex.org/W2101105183, https://openalex.org/W3135434033, https://openalex.org/W3169483174, https://openalex.org/W4386566460, https://openalex.org/W2963323070, https://openalex.org/W4287888679, https://openalex.org/W2610986956, https://openalex.org/W2889670144, https://openalex.org/W2891946694, https://openalex.org/W2988673764, https://openalex.org/W2951785908, https://openalex.org/W3103585424, https://openalex.org/W2964278185, https://openalex.org/W4288388982, https://openalex.org/W4287816021, https://openalex.org/W2962784628, https://openalex.org/W2729046720, https://openalex.org/W4287827771, https://openalex.org/W4319793149, https://openalex.org/W2114937339 |
| referenced_works_count | 26 |
| abstract_inverted_index.K | 181, 192 |
| abstract_inverted_index.a | 5, 10, 56, 71, 85, 101, 152, 188 |
| abstract_inverted_index.p | 185 |
| abstract_inverted_index.6) | 187 |
| abstract_inverted_index.In | 51 |
| abstract_inverted_index.QC | 256 |
| abstract_inverted_index.QG | 32, 60, 159, 253 |
| abstract_inverted_index.We | 118 |
| abstract_inverted_index.be | 90 |
| abstract_inverted_index.by | 251 |
| abstract_inverted_index.in | 13, 23, 33, 75, 100, 265, 298 |
| abstract_inverted_index.is | 9, 79 |
| abstract_inverted_index.it | 151 |
| abstract_inverted_index.of | 154, 158, 163, 190, 207, 210, 230, 247, 261, 268, 282, 300 |
| abstract_inverted_index.on | 31, 44, 81, 226 |
| abstract_inverted_index.to | 67, 92, 108, 198 |
| abstract_inverted_index.we | 54, 219 |
| abstract_inverted_index.(1) | 124, 140, 170 |
| abstract_inverted_index.(2) | 126, 145, 173 |
| abstract_inverted_index.(3) | 128, 176 |
| abstract_inverted_index.(4) | 179 |
| abstract_inverted_index.(5) | 183 |
| abstract_inverted_index.For | 161, 205 |
| abstract_inverted_index.OQL | 287 |
| abstract_inverted_index.Our | 77, 274 |
| abstract_inverted_index.Per | 143, 148 |
| abstract_inverted_index.QG, | 284 |
| abstract_inverted_index.The | 255 |
| abstract_inverted_index.Top | 180, 191 |
| abstract_inverted_index.all | 279, 294 |
| abstract_inverted_index.and | 21, 49, 98, 115, 130, 193, 216, 233, 244, 263, 270, 289, 303, 311 |
| abstract_inverted_index.are | 112 |
| abstract_inverted_index.can | 89 |
| abstract_inverted_index.few | 40 |
| abstract_inverted_index.for | 17, 59 |
| abstract_inverted_index.its | 18 |
| abstract_inverted_index.mT5 | 286 |
| abstract_inverted_index.our | 231, 252 |
| abstract_inverted_index.own | 232 |
| abstract_inverted_index.six | 155, 166 |
| abstract_inverted_index.the | 82, 94, 106, 202, 208, 242, 248, 266, 280, 283, 285, 295 |
| abstract_inverted_index.two | 135, 227, 235 |
| abstract_inverted_index.(QC) | 238 |
| abstract_inverted_index.(QG) | 3 |
| abstract_inverted_index.Beam | 174 |
| abstract_inverted_index.Top- | 184 |
| abstract_inverted_index.also | 220 |
| abstract_inverted_index.beam | 290 |
| abstract_inverted_index.been | 29, 42 |
| abstract_inverted_index.both | 113 |
| abstract_inverted_index.case | 267 |
| abstract_inverted_index.data | 137 |
| abstract_inverted_index.done | 43 |
| abstract_inverted_index.each | 162 |
| abstract_inverted_index.from | 4, 70, 201 |
| abstract_inverted_index.have | 28, 41 |
| abstract_inverted_index.idea | 83 |
| abstract_inverted_index.like | 36, 47 |
| abstract_inverted_index.ones | 297 |
| abstract_inverted_index.show | 276 |
| abstract_inverted_index.task | 12 |
| abstract_inverted_index.test | 203, 259 |
| abstract_inverted_index.that | 61, 84, 111, 240, 277 |
| abstract_inverted_index.this | 52 |
| abstract_inverted_index.used | 91, 197 |
| abstract_inverted_index.uses | 62 |
| abstract_inverted_index.very | 39 |
| abstract_inverted_index.were | 196 |
| abstract_inverted_index.with | 306 |
| abstract_inverted_index.(77%) | 302 |
| abstract_inverted_index.(96%) | 305 |
| abstract_inverted_index.36.60 | 307 |
| abstract_inverted_index.48.98 | 309 |
| abstract_inverted_index.63.38 | 312 |
| abstract_inverted_index.Line, | 144, 149 |
| abstract_inverted_index.Top-p | 194 |
| abstract_inverted_index.among | 278 |
| abstract_inverted_index.based | 80 |
| abstract_inverted_index.check | 241 |
| abstract_inverted_index.given | 6, 72 |
| abstract_inverted_index.learn | 93 |
| abstract_inverted_index.model | 88, 224 |
| abstract_inverted_index.other | 296 |
| abstract_inverted_index.terms | 299 |
| abstract_inverted_index.their | 132 |
| abstract_inverted_index.these | 164 |
| abstract_inverted_index.three | 120 |
| abstract_inverted_index.total | 153 |
| abstract_inverted_index.using | 134, 213 |
| abstract_inverted_index.which | 104 |
| abstract_inverted_index.words | 97 |
| abstract_inverted_index.work, | 53 |
| abstract_inverted_index.88.54% | 262 |
| abstract_inverted_index.95.76% | 264 |
| abstract_inverted_index.Arabic | 48 |
| abstract_inverted_index.Greedy | 171 |
| abstract_inverted_index.Random | 177 |
| abstract_inverted_index.allows | 105 |
| abstract_inverted_index.custom | 228 |
| abstract_inverted_index.making | 150 |
| abstract_inverted_index.method | 58 |
| abstract_inverted_index.models | 66, 107, 215, 239, 257 |
| abstract_inverted_index.showed | 258 |
| abstract_inverted_index.Bangla. | 50, 76 |
| abstract_inverted_index.Bleu_4, | 308 |
| abstract_inverted_index.METEOR, | 310 |
| abstract_inverted_index.ROUGE-L | 313 |
| abstract_inverted_index.Several | 26 |
| abstract_inverted_index.another | 222 |
| abstract_inverted_index.between | 96 |
| abstract_inverted_index.checks, | 272 |
| abstract_inverted_index.context | 7, 73, 102 |
| abstract_inverted_index.created | 234 |
| abstract_inverted_index.fields. | 25 |
| abstract_inverted_index.models. | 160, 254 |
| abstract_inverted_index.models: | 123 |
| abstract_inverted_index.natural | 14 |
| abstract_inverted_index.phrases | 99 |
| abstract_inverted_index.propose | 55 |
| abstract_inverted_index.quality | 209 |
| abstract_inverted_index.results | 275 |
| abstract_inverted_index.scores. | 314 |
| abstract_inverted_index.search, | 172, 175 |
| abstract_inverted_index.studies | 27 |
| abstract_inverted_index.various | 24 |
| abstract_inverted_index.Abstract | 0 |
| abstract_inverted_index.English, | 37 |
| abstract_inverted_index.Question | 1, 142, 147 |
| abstract_inverted_index.Sampling | 195 |
| abstract_inverted_index.accuracy | 260 |
| abstract_inverted_index.approach | 78, 288 |
| abstract_inverted_index.correct. | 117 |
| abstract_inverted_index.dataset. | 204 |
| abstract_inverted_index.datasets | 229 |
| abstract_inverted_index.decoding | 168, 217, 291 |
| abstract_inverted_index.generate | 68, 109, 199 |
| abstract_inverted_index.however, | 38 |
| abstract_inverted_index.language | 15, 65, 87 |
| abstract_inverted_index.question | 236 |
| abstract_inverted_index.relevant | 114 |
| abstract_inverted_index.variants | 281 |
| abstract_inverted_index.AQL—All | 141 |
| abstract_inverted_index.BanglaT5, | 125 |
| abstract_inverted_index.OQL—One | 146 |
| abstract_inverted_index.Sampling, | 178, 186 |
| abstract_inverted_index.algorithm | 292 |
| abstract_inverted_index.conducted | 30 |
| abstract_inverted_index.demanding | 11 |
| abstract_inverted_index.different | 121, 136, 156, 167, 214 |
| abstract_inverted_index.finetuned | 119 |
| abstract_inverted_index.generated | 212, 250 |
| abstract_inverted_index.languages | 35, 46 |
| abstract_inverted_index.mT5-base, | 127 |
| abstract_inverted_index.paragraph | 8, 74, 103 |
| abstract_inverted_index.practical | 19 |
| abstract_inverted_index.prospects | 22 |
| abstract_inverted_index.questions | 69, 110, 200, 211, 249 |
| abstract_inverted_index.relevancy | 243, 271, 301 |
| abstract_inverted_index.sampling, | 182 |
| abstract_inverted_index.variants, | 165 |
| abstract_inverted_index.BanglaBert | 225 |
| abstract_inverted_index.classifier | 237 |
| abstract_inverted_index.evaluation | 206 |
| abstract_inverted_index.fine-tuned | 221 |
| abstract_inverted_index.finetuning | 57 |
| abstract_inverted_index.formatting | 138 |
| abstract_inverted_index.generation | 2 |
| abstract_inverted_index.processing | 16 |
| abstract_inverted_index.variations | 157 |
| abstract_inverted_index.BanglaGPT2, | 129 |
| abstract_inverted_index.Grammatical | 245 |
| abstract_inverted_index.algorithms: | 169 |
| abstract_inverted_index.combination | 189 |
| abstract_inverted_index.correctness | 246, 269, 304 |
| abstract_inverted_index.pre-trained | 63 |
| abstract_inverted_index.techniques, | 218 |
| abstract_inverted_index.techniques: | 139 |
| abstract_inverted_index.transformer | 122, 223 |
| abstract_inverted_index.applications | 20 |
| abstract_inverted_index.capabilities | 133 |
| abstract_inverted_index.demonstrated | 131 |
| abstract_inverted_index.outperformed | 293 |
| abstract_inverted_index.grammatically | 116 |
| abstract_inverted_index.high-resource | 34 |
| abstract_inverted_index.relationships | 95 |
| abstract_inverted_index.resource-poor | 45 |
| abstract_inverted_index.respectively. | 273 |
| abstract_inverted_index.transformer-based | 64, 86 |
| cited_by_percentile_year.max | 97 |
| cited_by_percentile_year.min | 94 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 4 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/1 |
| sustainable_development_goals[0].score | 0.44999998807907104 |
| sustainable_development_goals[0].display_name | No poverty |
| citation_normalized_percentile.value | 0.86210934 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |