{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:TICII4KARWA5J4V3RRCLFZCDUX","short_pith_number":"pith:TICII4KA","schema_version":"1.0","canonical_sha256":"9a048471408d81d4f2bb8c44b2e443a5eb37991a7c53c9c298cdcc04ef062f1a","source":{"kind":"arxiv","id":"1702.07203","version":2},"attestation_state":"computed","paper":{"title":"Utilizing Lexical Similarity between Related, Low-resource Languages for Pivot-based SMT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Maulik Shah, Pradyot Prakash, Pushpak Bhattacharyya","submitted_at":"2017-02-23T13:13:53Z","abstract_excerpt":"We investigate pivot-based translation between related languages in a low resource, phrase-based SMT setting. We show that a subword-level pivot-based SMT model using a related pivot language is substantially better than word and morpheme-level pivot models. It is also highly competitive with the best direct translation model, which is encouraging as no direct source-target training corpus is used. We also show that combining multiple related language pivot models can rival a direct translation model. Thus, the use of subwords as translation units coupled with multiple related pivot languages "},"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":"1702.07203","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-23T13:13:53Z","cross_cats_sorted":[],"title_canon_sha256":"0ddce43d6bd26bd50e8b012a8a793b8b46e2ec2256f733308c0f1b7f1b1c83d0","abstract_canon_sha256":"5df3cde0d377f2769e9d8327cfaca4093411e72b7a6c33505b65161ce1acd36a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:39.395716Z","signature_b64":"vmR90GXpEz9xd3B3tQ6igXAo4lIQzklAKSg/dZlEd23IOXYj4fAgERkySiR4K6odw5U1/Pnz38lL2fOkZuUhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a048471408d81d4f2bb8c44b2e443a5eb37991a7c53c9c298cdcc04ef062f1a","last_reissued_at":"2026-05-18T00:33:39.395047Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:39.395047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Utilizing Lexical Similarity between Related, Low-resource Languages for Pivot-based SMT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Maulik Shah, Pradyot Prakash, Pushpak Bhattacharyya","submitted_at":"2017-02-23T13:13:53Z","abstract_excerpt":"We investigate pivot-based translation between related languages in a low resource, phrase-based SMT setting. We show that a subword-level pivot-based SMT model using a related pivot language is substantially better than word and morpheme-level pivot models. It is also highly competitive with the best direct translation model, which is encouraging as no direct source-target training corpus is used. We also show that combining multiple related language pivot models can rival a direct translation model. Thus, the use of subwords as translation units coupled with multiple related pivot languages "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07203","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1702.07203","created_at":"2026-05-18T00:33:39.395152+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.07203v2","created_at":"2026-05-18T00:33:39.395152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07203","created_at":"2026-05-18T00:33:39.395152+00:00"},{"alias_kind":"pith_short_12","alias_value":"TICII4KARWA5","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"TICII4KARWA5J4V3","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"TICII4KA","created_at":"2026-05-18T12:31:46.661854+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/TICII4KARWA5J4V3RRCLFZCDUX","json":"https://pith.science/pith/TICII4KARWA5J4V3RRCLFZCDUX.json","graph_json":"https://pith.science/api/pith-number/TICII4KARWA5J4V3RRCLFZCDUX/graph.json","events_json":"https://pith.science/api/pith-number/TICII4KARWA5J4V3RRCLFZCDUX/events.json","paper":"https://pith.science/paper/TICII4KA"},"agent_actions":{"view_html":"https://pith.science/pith/TICII4KARWA5J4V3RRCLFZCDUX","download_json":"https://pith.science/pith/TICII4KARWA5J4V3RRCLFZCDUX.json","view_paper":"https://pith.science/paper/TICII4KA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.07203&json=true","fetch_graph":"https://pith.science/api/pith-number/TICII4KARWA5J4V3RRCLFZCDUX/graph.json","fetch_events":"https://pith.science/api/pith-number/TICII4KARWA5J4V3RRCLFZCDUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TICII4KARWA5J4V3RRCLFZCDUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TICII4KARWA5J4V3RRCLFZCDUX/action/storage_attestation","attest_author":"https://pith.science/pith/TICII4KARWA5J4V3RRCLFZCDUX/action/author_attestation","sign_citation":"https://pith.science/pith/TICII4KARWA5J4V3RRCLFZCDUX/action/citation_signature","submit_replication":"https://pith.science/pith/TICII4KARWA5J4V3RRCLFZCDUX/action/replication_record"}},"created_at":"2026-05-18T00:33:39.395152+00:00","updated_at":"2026-05-18T00:33:39.395152+00:00"}