{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DAIHZR3RVJAGH6KDWMIXWI7DVE","short_pith_number":"pith:DAIHZR3R","schema_version":"1.0","canonical_sha256":"18107cc771aa4063f943b3117b23e3a907c1e401e3f45adad80ec25f22e5c4c0","source":{"kind":"arxiv","id":"1701.08339","version":1},"attestation_state":"computed","paper":{"title":"Using English as Pivot to Extract Persian-Italian Parallel Sentences from Non-Parallel Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ebrahim Ansari, Fatemeh Alimardani, M.H. Sadreddini, Mostafa Sheikhalishahi, Richard Wallace","submitted_at":"2017-01-29T00:22:24Z","abstract_excerpt":"The effectiveness of a statistical machine translation system (SMT) is very dependent upon the amount of parallel corpus used in the training phase. For low-resource language pairs there are not enough parallel corpora to build an accurate SMT. In this paper, a novel approach is presented to extract bilingual Persian-Italian parallel sentences from a non-parallel (comparable) corpus. In this study, English is used as the pivot language to compute the matching scores between source and target sentences and candidate selection phase. Additionally, a new monolingual sentence similarity metric, No"},"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":"1701.08339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-29T00:22:24Z","cross_cats_sorted":[],"title_canon_sha256":"facf17f267d18604afe6a668586902efab759cef4b340230d1a0cfb06c0111eb","abstract_canon_sha256":"f0a57a76f4d7090294c77860c940db3cf31df64aa397f6ed95690235a6c57964"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:54.487870Z","signature_b64":"0AM8B63+IRXe9YIfTqtrr7wKYY89lJALUNBmKsnjo+JbgBY6sQ+mOJlapr+frf1Y60LnVGIl7daO8bMscvM8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18107cc771aa4063f943b3117b23e3a907c1e401e3f45adad80ec25f22e5c4c0","last_reissued_at":"2026-05-18T00:51:54.487097Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:54.487097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using English as Pivot to Extract Persian-Italian Parallel Sentences from Non-Parallel Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ebrahim Ansari, Fatemeh Alimardani, M.H. Sadreddini, Mostafa Sheikhalishahi, Richard Wallace","submitted_at":"2017-01-29T00:22:24Z","abstract_excerpt":"The effectiveness of a statistical machine translation system (SMT) is very dependent upon the amount of parallel corpus used in the training phase. For low-resource language pairs there are not enough parallel corpora to build an accurate SMT. In this paper, a novel approach is presented to extract bilingual Persian-Italian parallel sentences from a non-parallel (comparable) corpus. In this study, English is used as the pivot language to compute the matching scores between source and target sentences and candidate selection phase. Additionally, a new monolingual sentence similarity metric, No"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.08339","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":"1701.08339","created_at":"2026-05-18T00:51:54.487228+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.08339v1","created_at":"2026-05-18T00:51:54.487228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.08339","created_at":"2026-05-18T00:51:54.487228+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAIHZR3RVJAG","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAIHZR3RVJAGH6KD","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAIHZR3R","created_at":"2026-05-18T12:31:10.602751+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/DAIHZR3RVJAGH6KDWMIXWI7DVE","json":"https://pith.science/pith/DAIHZR3RVJAGH6KDWMIXWI7DVE.json","graph_json":"https://pith.science/api/pith-number/DAIHZR3RVJAGH6KDWMIXWI7DVE/graph.json","events_json":"https://pith.science/api/pith-number/DAIHZR3RVJAGH6KDWMIXWI7DVE/events.json","paper":"https://pith.science/paper/DAIHZR3R"},"agent_actions":{"view_html":"https://pith.science/pith/DAIHZR3RVJAGH6KDWMIXWI7DVE","download_json":"https://pith.science/pith/DAIHZR3RVJAGH6KDWMIXWI7DVE.json","view_paper":"https://pith.science/paper/DAIHZR3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.08339&json=true","fetch_graph":"https://pith.science/api/pith-number/DAIHZR3RVJAGH6KDWMIXWI7DVE/graph.json","fetch_events":"https://pith.science/api/pith-number/DAIHZR3RVJAGH6KDWMIXWI7DVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAIHZR3RVJAGH6KDWMIXWI7DVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAIHZR3RVJAGH6KDWMIXWI7DVE/action/storage_attestation","attest_author":"https://pith.science/pith/DAIHZR3RVJAGH6KDWMIXWI7DVE/action/author_attestation","sign_citation":"https://pith.science/pith/DAIHZR3RVJAGH6KDWMIXWI7DVE/action/citation_signature","submit_replication":"https://pith.science/pith/DAIHZR3RVJAGH6KDWMIXWI7DVE/action/replication_record"}},"created_at":"2026-05-18T00:51:54.487228+00:00","updated_at":"2026-05-18T00:51:54.487228+00:00"}