{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CF4CERKSBRSVF5PF6V3GS7KDSW","short_pith_number":"pith:CF4CERKS","schema_version":"1.0","canonical_sha256":"11782245520c6552f5e5f576697d43959be7c1039c1edd0d8ca9689945ed115d","source":{"kind":"arxiv","id":"2412.16877","version":1},"attestation_state":"computed","paper":{"title":"Reconsidering SMT Over NMT for Closely Related Languages: A Case Study of Persian-Hindi Pair","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Pushpak Bhattacharyya, Waisullah Yousofi","submitted_at":"2024-12-22T06:12:46Z","abstract_excerpt":"This paper demonstrates that Phrase-Based Statistical Machine Translation (PBSMT) can outperform Transformer-based Neural Machine Translation (NMT) in moderate-resource scenarios, specifically for structurally similar languages, like the Persian-Hindi pair. Despite the Transformer architecture's typical preference for large parallel corpora, our results show that PBSMT achieves a BLEU score of 66.32, significantly exceeding the Transformer-NMT score of 53.7 on the same dataset. Additionally, we explore variations of the SMT architecture, including training on Romanized text and modifying the w"},"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":"2412.16877","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T06:12:46Z","cross_cats_sorted":[],"title_canon_sha256":"a23e8aeca0e71f64dbbd62328c0dd075217470ee3ace9dbfca7a79c4d595de29","abstract_canon_sha256":"12c99001a6cd153e6acbf282872149e29f0cb897e6a656b41812a417e8239f50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:14.050786Z","signature_b64":"9lMtco3YHFYqkRNrq88vBXOfvIEeggZyzU4/4mR+K6+Da1lFNCJL4JIWv1ZEMQn5xGtinChPr0oyQBfrE2ZNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11782245520c6552f5e5f576697d43959be7c1039c1edd0d8ca9689945ed115d","last_reissued_at":"2026-07-05T09:53:14.050355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:14.050355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reconsidering SMT Over NMT for Closely Related Languages: A Case Study of Persian-Hindi Pair","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Pushpak Bhattacharyya, Waisullah Yousofi","submitted_at":"2024-12-22T06:12:46Z","abstract_excerpt":"This paper demonstrates that Phrase-Based Statistical Machine Translation (PBSMT) can outperform Transformer-based Neural Machine Translation (NMT) in moderate-resource scenarios, specifically for structurally similar languages, like the Persian-Hindi pair. Despite the Transformer architecture's typical preference for large parallel corpora, our results show that PBSMT achieves a BLEU score of 66.32, significantly exceeding the Transformer-NMT score of 53.7 on the same dataset. Additionally, we explore variations of the SMT architecture, including training on Romanized text and modifying the w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16877","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/2412.16877/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":"2412.16877","created_at":"2026-07-05T09:53:14.050411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16877v1","created_at":"2026-07-05T09:53:14.050411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16877","created_at":"2026-07-05T09:53:14.050411+00:00"},{"alias_kind":"pith_short_12","alias_value":"CF4CERKSBRSV","created_at":"2026-07-05T09:53:14.050411+00:00"},{"alias_kind":"pith_short_16","alias_value":"CF4CERKSBRSVF5PF","created_at":"2026-07-05T09:53:14.050411+00:00"},{"alias_kind":"pith_short_8","alias_value":"CF4CERKS","created_at":"2026-07-05T09:53:14.050411+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CF4CERKSBRSVF5PF6V3GS7KDSW","json":"https://pith.science/pith/CF4CERKSBRSVF5PF6V3GS7KDSW.json","graph_json":"https://pith.science/api/pith-number/CF4CERKSBRSVF5PF6V3GS7KDSW/graph.json","events_json":"https://pith.science/api/pith-number/CF4CERKSBRSVF5PF6V3GS7KDSW/events.json","paper":"https://pith.science/paper/CF4CERKS"},"agent_actions":{"view_html":"https://pith.science/pith/CF4CERKSBRSVF5PF6V3GS7KDSW","download_json":"https://pith.science/pith/CF4CERKSBRSVF5PF6V3GS7KDSW.json","view_paper":"https://pith.science/paper/CF4CERKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16877&json=true","fetch_graph":"https://pith.science/api/pith-number/CF4CERKSBRSVF5PF6V3GS7KDSW/graph.json","fetch_events":"https://pith.science/api/pith-number/CF4CERKSBRSVF5PF6V3GS7KDSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CF4CERKSBRSVF5PF6V3GS7KDSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CF4CERKSBRSVF5PF6V3GS7KDSW/action/storage_attestation","attest_author":"https://pith.science/pith/CF4CERKSBRSVF5PF6V3GS7KDSW/action/author_attestation","sign_citation":"https://pith.science/pith/CF4CERKSBRSVF5PF6V3GS7KDSW/action/citation_signature","submit_replication":"https://pith.science/pith/CF4CERKSBRSVF5PF6V3GS7KDSW/action/replication_record"}},"created_at":"2026-07-05T09:53:14.050411+00:00","updated_at":"2026-07-05T09:53:14.050411+00:00"}