{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AJ5TJQMBD6UOY7CQ6O54P27JZ2","short_pith_number":"pith:AJ5TJQMB","schema_version":"1.0","canonical_sha256":"027b34c1811fa8ec7c50f3bbc7ebe9cea15c6184b34e07dab327c00d835ae047","source":{"kind":"arxiv","id":"1909.02855","version":2},"attestation_state":"computed","paper":{"title":"Don't Forget the Long Tail! A Comprehensive Analysis of Morphological Generalization in Bilingual Lexicon Induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ann Copestake, Edouard Grave, Paula Czarnowska, Ryan Cotterell, Sebastian Ruder","submitted_at":"2019-09-06T12:27:43Z","abstract_excerpt":"Human translators routinely have to translate rare inflections of words - due to the Zipfian distribution of words in a language. When translating from Spanish, a good translator would have no problem identifying the proper translation of a statistically rare inflection such as habl\\'aramos. Note the lexeme itself, hablar, is relatively common. In this work, we investigate whether state-of-the-art bilingual lexicon inducers are capable of learning this kind of generalization. We introduce 40 morphologically complete dictionaries in 10 languages and evaluate three of the state-of-the-art models"},"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":"1909.02855","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-06T12:27:43Z","cross_cats_sorted":[],"title_canon_sha256":"6b101a704ed739c7467853d5bb0de6cbc79e69497161404aebbc60eceaccb920","abstract_canon_sha256":"1c37e10e4e8b86d8d44b17777559820f83fdb451843796f9d78daf8b36a498b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:13:55.429936Z","signature_b64":"zfh7hNmOisA9nNo4In7thiLycwsKV/NLumVotim7UQrsuchDtib8Y+dWhAan6tYdE5U2KomECJyBNv+2WaKmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"027b34c1811fa8ec7c50f3bbc7ebe9cea15c6184b34e07dab327c00d835ae047","last_reissued_at":"2026-07-05T00:13:55.429523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:13:55.429523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Don't Forget the Long Tail! A Comprehensive Analysis of Morphological Generalization in Bilingual Lexicon Induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ann Copestake, Edouard Grave, Paula Czarnowska, Ryan Cotterell, Sebastian Ruder","submitted_at":"2019-09-06T12:27:43Z","abstract_excerpt":"Human translators routinely have to translate rare inflections of words - due to the Zipfian distribution of words in a language. When translating from Spanish, a good translator would have no problem identifying the proper translation of a statistically rare inflection such as habl\\'aramos. Note the lexeme itself, hablar, is relatively common. In this work, we investigate whether state-of-the-art bilingual lexicon inducers are capable of learning this kind of generalization. We introduce 40 morphologically complete dictionaries in 10 languages and evaluate three of the state-of-the-art models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02855","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.02855/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":"1909.02855","created_at":"2026-07-05T00:13:55.429588+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.02855v2","created_at":"2026-07-05T00:13:55.429588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02855","created_at":"2026-07-05T00:13:55.429588+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJ5TJQMBD6UO","created_at":"2026-07-05T00:13:55.429588+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJ5TJQMBD6UOY7CQ","created_at":"2026-07-05T00:13:55.429588+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJ5TJQMB","created_at":"2026-07-05T00:13:55.429588+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/AJ5TJQMBD6UOY7CQ6O54P27JZ2","json":"https://pith.science/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2.json","graph_json":"https://pith.science/api/pith-number/AJ5TJQMBD6UOY7CQ6O54P27JZ2/graph.json","events_json":"https://pith.science/api/pith-number/AJ5TJQMBD6UOY7CQ6O54P27JZ2/events.json","paper":"https://pith.science/paper/AJ5TJQMB"},"agent_actions":{"view_html":"https://pith.science/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2","download_json":"https://pith.science/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2.json","view_paper":"https://pith.science/paper/AJ5TJQMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.02855&json=true","fetch_graph":"https://pith.science/api/pith-number/AJ5TJQMBD6UOY7CQ6O54P27JZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/AJ5TJQMBD6UOY7CQ6O54P27JZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2/action/storage_attestation","attest_author":"https://pith.science/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2/action/author_attestation","sign_citation":"https://pith.science/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2/action/citation_signature","submit_replication":"https://pith.science/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2/action/replication_record"}},"created_at":"2026-07-05T00:13:55.429588+00:00","updated_at":"2026-07-05T00:13:55.429588+00:00"}