{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7TZYMEC7C6BMMRPHJLXKPCUGXE","short_pith_number":"pith:7TZYMEC7","schema_version":"1.0","canonical_sha256":"fcf386105f1782c645e74aeea78a86b92f025dc4cf96c7be7f602af21a2f3106","source":{"kind":"arxiv","id":"1911.07613","version":1},"attestation_state":"computed","paper":{"title":"A Subword Level Language Model for Bangla Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aisha Khatun, Anisur Rahman, Ayesha Tasnim, Hemayet Ahmed Chowdhury, Md. Saiful Islam","submitted_at":"2019-11-15T08:22:33Z","abstract_excerpt":"Language models are at the core of natural language processing. The ability to represent natural language gives rise to its applications in numerous NLP tasks including text classification, summarization, and translation. Research in this area is very limited in Bangla due to the scarcity of resources, except for some count-based models and very recent neural language models being proposed, which are all based on words and limited in practical tasks due to their high perplexity. This paper attempts to approach this issue of perplexity and proposes a subword level neural language model with the"},"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":"1911.07613","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-11-15T08:22:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4229c8935e0d64f19e7e0d523939df0d54a038ab8a0b49f68555a2e225100bdc","abstract_canon_sha256":"4de6f3e9de68d9a3680246d507178540e69c68d53be21f5d6b7cb4294762daca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:05.766109Z","signature_b64":"79QbOAq6nem5wQrtWwgkwRZU0nzGCWtxI9zQwIvxPkZq0BxwXWmYPB4eUqsLhRybNW4R3BW1G2LTRIFTV4V/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcf386105f1782c645e74aeea78a86b92f025dc4cf96c7be7f602af21a2f3106","last_reissued_at":"2026-07-05T00:20:05.765584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:05.765584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Subword Level Language Model for Bangla Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aisha Khatun, Anisur Rahman, Ayesha Tasnim, Hemayet Ahmed Chowdhury, Md. Saiful Islam","submitted_at":"2019-11-15T08:22:33Z","abstract_excerpt":"Language models are at the core of natural language processing. The ability to represent natural language gives rise to its applications in numerous NLP tasks including text classification, summarization, and translation. Research in this area is very limited in Bangla due to the scarcity of resources, except for some count-based models and very recent neural language models being proposed, which are all based on words and limited in practical tasks due to their high perplexity. This paper attempts to approach this issue of perplexity and proposes a subword level neural language model with the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.07613","kind":"arxiv","version":1},"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/1911.07613/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":"1911.07613","created_at":"2026-07-05T00:20:05.765640+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.07613v1","created_at":"2026-07-05T00:20:05.765640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.07613","created_at":"2026-07-05T00:20:05.765640+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TZYMEC7C6BM","created_at":"2026-07-05T00:20:05.765640+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TZYMEC7C6BMMRPH","created_at":"2026-07-05T00:20:05.765640+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TZYMEC7","created_at":"2026-07-05T00:20:05.765640+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":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7TZYMEC7C6BMMRPHJLXKPCUGXE","json":"https://pith.science/pith/7TZYMEC7C6BMMRPHJLXKPCUGXE.json","graph_json":"https://pith.science/api/pith-number/7TZYMEC7C6BMMRPHJLXKPCUGXE/graph.json","events_json":"https://pith.science/api/pith-number/7TZYMEC7C6BMMRPHJLXKPCUGXE/events.json","paper":"https://pith.science/paper/7TZYMEC7"},"agent_actions":{"view_html":"https://pith.science/pith/7TZYMEC7C6BMMRPHJLXKPCUGXE","download_json":"https://pith.science/pith/7TZYMEC7C6BMMRPHJLXKPCUGXE.json","view_paper":"https://pith.science/paper/7TZYMEC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.07613&json=true","fetch_graph":"https://pith.science/api/pith-number/7TZYMEC7C6BMMRPHJLXKPCUGXE/graph.json","fetch_events":"https://pith.science/api/pith-number/7TZYMEC7C6BMMRPHJLXKPCUGXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TZYMEC7C6BMMRPHJLXKPCUGXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TZYMEC7C6BMMRPHJLXKPCUGXE/action/storage_attestation","attest_author":"https://pith.science/pith/7TZYMEC7C6BMMRPHJLXKPCUGXE/action/author_attestation","sign_citation":"https://pith.science/pith/7TZYMEC7C6BMMRPHJLXKPCUGXE/action/citation_signature","submit_replication":"https://pith.science/pith/7TZYMEC7C6BMMRPHJLXKPCUGXE/action/replication_record"}},"created_at":"2026-07-05T00:20:05.765640+00:00","updated_at":"2026-07-05T00:20:05.765640+00:00"}