{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CUFBVWZUWFGLNVSLRTTHPP3Y6E","short_pith_number":"pith:CUFBVWZU","schema_version":"1.0","canonical_sha256":"150a1adb34b14cb6d64b8ce677bf78f12e82634123016fde88c1f4dad504c9a8","source":{"kind":"arxiv","id":"1709.05631","version":2},"attestation_state":"computed","paper":{"title":"Unwritten Languages Demand Attention Too! Word Discovery with Encoder-Decoder Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandre Berard, Aline Villavicencio, Laurent Besacier, Marcely Zanon Boito","submitted_at":"2017-09-17T09:36:40Z","abstract_excerpt":"Word discovery is the task of extracting words from unsegmented text. In this paper we examine to what extent neural networks can be applied to this task in a realistic unwritten language scenario, where only small corpora and limited annotations are available. We investigate two scenarios: one with no supervision and another with limited supervision with access to the most frequent words. Obtained results show that it is possible to retrieve at least 27% of the gold standard vocabulary by training an encoder-decoder neural machine translation system with only 5,157 sentences. This result is c"},"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":"1709.05631","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-09-17T09:36:40Z","cross_cats_sorted":[],"title_canon_sha256":"2e8b2bdb34a3fe664d2f643818c1f90c6ace40de24e23ac3e29330522c45c6b5","abstract_canon_sha256":"ef9668d28278e2371e06cc8c2724660f657732f7108f191d2417903148e2e22e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:54.477249Z","signature_b64":"CLcfUdL+daMu158wYk/FKp91pA+RSQAK6SO6xNmPTzBUR8aQ5Idx9ElZuLs1QGX366TlRcePBhMtWJ4F6DLxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"150a1adb34b14cb6d64b8ce677bf78f12e82634123016fde88c1f4dad504c9a8","last_reissued_at":"2026-05-18T00:34:54.476567Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:54.476567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unwritten Languages Demand Attention Too! Word Discovery with Encoder-Decoder Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandre Berard, Aline Villavicencio, Laurent Besacier, Marcely Zanon Boito","submitted_at":"2017-09-17T09:36:40Z","abstract_excerpt":"Word discovery is the task of extracting words from unsegmented text. In this paper we examine to what extent neural networks can be applied to this task in a realistic unwritten language scenario, where only small corpora and limited annotations are available. We investigate two scenarios: one with no supervision and another with limited supervision with access to the most frequent words. Obtained results show that it is possible to retrieve at least 27% of the gold standard vocabulary by training an encoder-decoder neural machine translation system with only 5,157 sentences. This result is c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.05631","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":"1709.05631","created_at":"2026-05-18T00:34:54.476681+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.05631v2","created_at":"2026-05-18T00:34:54.476681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.05631","created_at":"2026-05-18T00:34:54.476681+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUFBVWZUWFGL","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUFBVWZUWFGLNVSL","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUFBVWZU","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/CUFBVWZUWFGLNVSLRTTHPP3Y6E","json":"https://pith.science/pith/CUFBVWZUWFGLNVSLRTTHPP3Y6E.json","graph_json":"https://pith.science/api/pith-number/CUFBVWZUWFGLNVSLRTTHPP3Y6E/graph.json","events_json":"https://pith.science/api/pith-number/CUFBVWZUWFGLNVSLRTTHPP3Y6E/events.json","paper":"https://pith.science/paper/CUFBVWZU"},"agent_actions":{"view_html":"https://pith.science/pith/CUFBVWZUWFGLNVSLRTTHPP3Y6E","download_json":"https://pith.science/pith/CUFBVWZUWFGLNVSLRTTHPP3Y6E.json","view_paper":"https://pith.science/paper/CUFBVWZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.05631&json=true","fetch_graph":"https://pith.science/api/pith-number/CUFBVWZUWFGLNVSLRTTHPP3Y6E/graph.json","fetch_events":"https://pith.science/api/pith-number/CUFBVWZUWFGLNVSLRTTHPP3Y6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUFBVWZUWFGLNVSLRTTHPP3Y6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUFBVWZUWFGLNVSLRTTHPP3Y6E/action/storage_attestation","attest_author":"https://pith.science/pith/CUFBVWZUWFGLNVSLRTTHPP3Y6E/action/author_attestation","sign_citation":"https://pith.science/pith/CUFBVWZUWFGLNVSLRTTHPP3Y6E/action/citation_signature","submit_replication":"https://pith.science/pith/CUFBVWZUWFGLNVSLRTTHPP3Y6E/action/replication_record"}},"created_at":"2026-05-18T00:34:54.476681+00:00","updated_at":"2026-05-18T00:34:54.476681+00:00"}