{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:GBRDSX47XHRS5LRL34MH3GWMXV","short_pith_number":"pith:GBRDSX47","schema_version":"1.0","canonical_sha256":"3062395f9fb9e32eae2bdf187d9accbd74b6b88703056f1111993905bcf4a31e","source":{"kind":"arxiv","id":"1609.01188","version":1},"attestation_state":"computed","paper":{"title":"Bi-Text Alignment of Movie Subtitles for Spoken English-Arabic Statistical Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fahad Al-Obaidli, Preslav Nakov, Stephen Cox","submitted_at":"2016-09-05T14:55:31Z","abstract_excerpt":"We describe efforts towards getting better resources for English-Arabic machine translation of spoken text. In particular, we look at movie subtitles as a unique, rich resource, as subtitles in one language often get translated into other languages. Movie subtitles are not new as a resource and have been explored in previous research; however, here we create a much larger bi-text (the biggest to date), and we further generate better quality alignment for it. Given the subtitles for the same movie in different languages, a key problem is how to align them at the fragment level. Typically, this "},"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":"1609.01188","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-05T14:55:31Z","cross_cats_sorted":[],"title_canon_sha256":"f12b168ba4799dc4d88ba3b4dd631d7842cf611e638d6e0653ed9985fadc29a0","abstract_canon_sha256":"d49f71c4b2407cdb3d8975997b949e7befd35a82fe56da2a13b1111254009258"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:06:18.758689Z","signature_b64":"TIbRB7x6R3nz1+QU5Ld8WcXkQrnGzT7Q14DUyvWHXgcY7yfOGUe3RpUKEq6zf32yiT4aYDFvhbwskjcVFG9vDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3062395f9fb9e32eae2bdf187d9accbd74b6b88703056f1111993905bcf4a31e","last_reissued_at":"2026-05-18T01:06:18.758191Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:06:18.758191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bi-Text Alignment of Movie Subtitles for Spoken English-Arabic Statistical Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fahad Al-Obaidli, Preslav Nakov, Stephen Cox","submitted_at":"2016-09-05T14:55:31Z","abstract_excerpt":"We describe efforts towards getting better resources for English-Arabic machine translation of spoken text. In particular, we look at movie subtitles as a unique, rich resource, as subtitles in one language often get translated into other languages. Movie subtitles are not new as a resource and have been explored in previous research; however, here we create a much larger bi-text (the biggest to date), and we further generate better quality alignment for it. Given the subtitles for the same movie in different languages, a key problem is how to align them at the fragment level. Typically, this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.01188","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":""},"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":"1609.01188","created_at":"2026-05-18T01:06:18.758264+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.01188v1","created_at":"2026-05-18T01:06:18.758264+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.01188","created_at":"2026-05-18T01:06:18.758264+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBRDSX47XHRS","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBRDSX47XHRS5LRL","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBRDSX47","created_at":"2026-05-18T12:30:15.759754+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/GBRDSX47XHRS5LRL34MH3GWMXV","json":"https://pith.science/pith/GBRDSX47XHRS5LRL34MH3GWMXV.json","graph_json":"https://pith.science/api/pith-number/GBRDSX47XHRS5LRL34MH3GWMXV/graph.json","events_json":"https://pith.science/api/pith-number/GBRDSX47XHRS5LRL34MH3GWMXV/events.json","paper":"https://pith.science/paper/GBRDSX47"},"agent_actions":{"view_html":"https://pith.science/pith/GBRDSX47XHRS5LRL34MH3GWMXV","download_json":"https://pith.science/pith/GBRDSX47XHRS5LRL34MH3GWMXV.json","view_paper":"https://pith.science/paper/GBRDSX47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.01188&json=true","fetch_graph":"https://pith.science/api/pith-number/GBRDSX47XHRS5LRL34MH3GWMXV/graph.json","fetch_events":"https://pith.science/api/pith-number/GBRDSX47XHRS5LRL34MH3GWMXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBRDSX47XHRS5LRL34MH3GWMXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBRDSX47XHRS5LRL34MH3GWMXV/action/storage_attestation","attest_author":"https://pith.science/pith/GBRDSX47XHRS5LRL34MH3GWMXV/action/author_attestation","sign_citation":"https://pith.science/pith/GBRDSX47XHRS5LRL34MH3GWMXV/action/citation_signature","submit_replication":"https://pith.science/pith/GBRDSX47XHRS5LRL34MH3GWMXV/action/replication_record"}},"created_at":"2026-05-18T01:06:18.758264+00:00","updated_at":"2026-05-18T01:06:18.758264+00:00"}