{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FCK4ZLHGBEWORBTUBCULDMSSFG","short_pith_number":"pith:FCK4ZLHG","schema_version":"1.0","canonical_sha256":"2895ccace6092ce8867408a8b1b25229a637880d5cb47cec5d7eaa0bbdd12372","source":{"kind":"arxiv","id":"1809.07807","version":1},"attestation_state":"computed","paper":{"title":"Bootstrapping Transliteration with Constrained Discovery for Low-Resource Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Roth, Jordan Kodner, Shyam Upadhyay","submitted_at":"2018-09-20T19:05:29Z","abstract_excerpt":"Generating the English transliteration of a name written in a foreign script is an important and challenging step in multilingual knowledge acquisition and information extraction. Existing approaches to transliteration generation require a large (>5000) number of training examples. This difficulty contrasts with transliteration discovery, a somewhat easier task that involves picking a plausible transliteration from a given list. In this work, we present a bootstrapping algorithm that uses constrained discovery to improve generation, and can be used with as few as 500 training examples, which 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":"1809.07807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-20T19:05:29Z","cross_cats_sorted":[],"title_canon_sha256":"2fb3b02cb5b2156021d780e8c043fe52a6b30b273c46d5fd9ada97962647d10b","abstract_canon_sha256":"72bb033c7808961afd63b74d566213b2df9860cacff23941f51a10d46f19273b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:13.229193Z","signature_b64":"XW+pakSrHt7TPRbUXHDW01tK8czAlUhlhmcfIJ5wc8SnicHXwECswwU5zgrqyS7wvahF2Wsl7BGn1KuCVUEgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2895ccace6092ce8867408a8b1b25229a637880d5cb47cec5d7eaa0bbdd12372","last_reissued_at":"2026-05-18T00:05:13.228651Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:13.228651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bootstrapping Transliteration with Constrained Discovery for Low-Resource Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Roth, Jordan Kodner, Shyam Upadhyay","submitted_at":"2018-09-20T19:05:29Z","abstract_excerpt":"Generating the English transliteration of a name written in a foreign script is an important and challenging step in multilingual knowledge acquisition and information extraction. Existing approaches to transliteration generation require a large (>5000) number of training examples. This difficulty contrasts with transliteration discovery, a somewhat easier task that involves picking a plausible transliteration from a given list. In this work, we present a bootstrapping algorithm that uses constrained discovery to improve generation, and can be used with as few as 500 training examples, which w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.07807","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":"1809.07807","created_at":"2026-05-18T00:05:13.228738+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.07807v1","created_at":"2026-05-18T00:05:13.228738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.07807","created_at":"2026-05-18T00:05:13.228738+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCK4ZLHGBEWO","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCK4ZLHGBEWORBTU","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCK4ZLHG","created_at":"2026-05-18T12:32:22.470017+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/FCK4ZLHGBEWORBTUBCULDMSSFG","json":"https://pith.science/pith/FCK4ZLHGBEWORBTUBCULDMSSFG.json","graph_json":"https://pith.science/api/pith-number/FCK4ZLHGBEWORBTUBCULDMSSFG/graph.json","events_json":"https://pith.science/api/pith-number/FCK4ZLHGBEWORBTUBCULDMSSFG/events.json","paper":"https://pith.science/paper/FCK4ZLHG"},"agent_actions":{"view_html":"https://pith.science/pith/FCK4ZLHGBEWORBTUBCULDMSSFG","download_json":"https://pith.science/pith/FCK4ZLHGBEWORBTUBCULDMSSFG.json","view_paper":"https://pith.science/paper/FCK4ZLHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.07807&json=true","fetch_graph":"https://pith.science/api/pith-number/FCK4ZLHGBEWORBTUBCULDMSSFG/graph.json","fetch_events":"https://pith.science/api/pith-number/FCK4ZLHGBEWORBTUBCULDMSSFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCK4ZLHGBEWORBTUBCULDMSSFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCK4ZLHGBEWORBTUBCULDMSSFG/action/storage_attestation","attest_author":"https://pith.science/pith/FCK4ZLHGBEWORBTUBCULDMSSFG/action/author_attestation","sign_citation":"https://pith.science/pith/FCK4ZLHGBEWORBTUBCULDMSSFG/action/citation_signature","submit_replication":"https://pith.science/pith/FCK4ZLHGBEWORBTUBCULDMSSFG/action/replication_record"}},"created_at":"2026-05-18T00:05:13.228738+00:00","updated_at":"2026-05-18T00:05:13.228738+00:00"}