{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BVQOC5PZLUX5PXFWQU4X63JHGS","short_pith_number":"pith:BVQOC5PZ","schema_version":"1.0","canonical_sha256":"0d60e175f95d2fd7dcb685397f6d2734b9c49a34822d40f63d526c9629486705","source":{"kind":"arxiv","id":"2107.03844","version":3},"attestation_state":"computed","paper":{"title":"A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Akib Khan, Arid Hasan, Firoj Alam, Janntatul Tajrin, Naira Khan, Shammur Absar Chowdhury, Tanvirul Alam","submitted_at":"2021-07-08T13:49:46Z","abstract_excerpt":"Bangla -- ranked as the 6th most widely spoken language across the world (https://www.ethnologue.com/guides/ethnologue200), with 230 million native speakers -- is still considered as a low-resource language in the natural language processing (NLP) community. With three decades of research, Bangla NLP (BNLP) is still lagging behind mainly due to the scarcity of resources and the challenges that come with it. There is sparse work in different areas of BNLP; however, a thorough survey reporting previous work and recent advances is yet to be done. In this study, we first provide a review of Bangla"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2107.03844","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-08T13:49:46Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"ce358bffc61ef6268d71cb12ca24d8a5929ca1479576f3d1bc181947755a4c13","abstract_canon_sha256":"8bc18c74a75b8bbacec63bd6c9fd1ad155122741119fb10292232954b4a31527"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:34.593871Z","signature_b64":"7GaIos/eKM5q62M6VsOmVBuGWcf9Am9SzTj8ZN/b9KqzQCPe8F+OrGI54RGOdrmKm8ArzOlhNqxOOV/ryHHRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d60e175f95d2fd7dcb685397f6d2734b9c49a34822d40f63d526c9629486705","last_reissued_at":"2026-07-05T03:00:34.593440Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:34.593440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Akib Khan, Arid Hasan, Firoj Alam, Janntatul Tajrin, Naira Khan, Shammur Absar Chowdhury, Tanvirul Alam","submitted_at":"2021-07-08T13:49:46Z","abstract_excerpt":"Bangla -- ranked as the 6th most widely spoken language across the world (https://www.ethnologue.com/guides/ethnologue200), with 230 million native speakers -- is still considered as a low-resource language in the natural language processing (NLP) community. With three decades of research, Bangla NLP (BNLP) is still lagging behind mainly due to the scarcity of resources and the challenges that come with it. There is sparse work in different areas of BNLP; however, a thorough survey reporting previous work and recent advances is yet to be done. In this study, we first provide a review of Bangla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03844","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.03844/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2107.03844","created_at":"2026-07-05T03:00:34.593499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.03844v3","created_at":"2026-07-05T03:00:34.593499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03844","created_at":"2026-07-05T03:00:34.593499+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVQOC5PZLUX5","created_at":"2026-07-05T03:00:34.593499+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVQOC5PZLUX5PXFW","created_at":"2026-07-05T03:00:34.593499+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVQOC5PZ","created_at":"2026-07-05T03:00:34.593499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05104","citing_title":"BnBERT-iPET: Sparse Few-Shot Language Modeling for Bengali via Lottery Ticket Pruning","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BVQOC5PZLUX5PXFWQU4X63JHGS","json":"https://pith.science/pith/BVQOC5PZLUX5PXFWQU4X63JHGS.json","graph_json":"https://pith.science/api/pith-number/BVQOC5PZLUX5PXFWQU4X63JHGS/graph.json","events_json":"https://pith.science/api/pith-number/BVQOC5PZLUX5PXFWQU4X63JHGS/events.json","paper":"https://pith.science/paper/BVQOC5PZ"},"agent_actions":{"view_html":"https://pith.science/pith/BVQOC5PZLUX5PXFWQU4X63JHGS","download_json":"https://pith.science/pith/BVQOC5PZLUX5PXFWQU4X63JHGS.json","view_paper":"https://pith.science/paper/BVQOC5PZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.03844&json=true","fetch_graph":"https://pith.science/api/pith-number/BVQOC5PZLUX5PXFWQU4X63JHGS/graph.json","fetch_events":"https://pith.science/api/pith-number/BVQOC5PZLUX5PXFWQU4X63JHGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVQOC5PZLUX5PXFWQU4X63JHGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVQOC5PZLUX5PXFWQU4X63JHGS/action/storage_attestation","attest_author":"https://pith.science/pith/BVQOC5PZLUX5PXFWQU4X63JHGS/action/author_attestation","sign_citation":"https://pith.science/pith/BVQOC5PZLUX5PXFWQU4X63JHGS/action/citation_signature","submit_replication":"https://pith.science/pith/BVQOC5PZLUX5PXFWQU4X63JHGS/action/replication_record"}},"created_at":"2026-07-05T03:00:34.593499+00:00","updated_at":"2026-07-05T03:00:34.593499+00:00"}