{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LBV6FXCJRKEWFMOJCTAWGOZYNI","short_pith_number":"pith:LBV6FXCJ","schema_version":"1.0","canonical_sha256":"586be2dc498a8962b1c914c1633b386a2b3eaee8525476df2fa9e531e4d4ac61","source":{"kind":"arxiv","id":"1802.04559","version":1},"attestation_state":"computed","paper":{"title":"Sentence Boundary Detection for French with Subword-Level Information Vectors and Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carlos-Emiliano Gonz\\'alez-Gallardo, Juan-Manuel Torres-Moreno","submitted_at":"2018-02-13T11:04:07Z","abstract_excerpt":"In this work we tackle the problem of sentence boundary detection applied to French as a binary classification task (\"sentence boundary\" or \"not sentence boundary\"). We combine convolutional neural networks with subword-level information vectors, which are word embedding representations learned from Wikipedia that take advantage of the words morphology; so each word is represented as a bag of their character n-grams.\n  We decide to use a big written dataset (French Gigaword) instead of standard size transcriptions to train and evaluate the proposed architectures with the intention of using the"},"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":"1802.04559","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-13T11:04:07Z","cross_cats_sorted":[],"title_canon_sha256":"b1f88a440939275ac3933911c9c18be5943dc92e06c269ef402ddcee206c57bc","abstract_canon_sha256":"aab33b0a81c6fdeafd46c8eaf28c97f9892c667e373cf7bb202e3e058ca98079"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:42.109968Z","signature_b64":"oiak2YxxA5IJq58gUcRsMq0o1GJxcLJOXM35bl/blqGWlsqZTp9FpXBQHhEMeEPyPvCdaud0yUWlKaaO+faBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"586be2dc498a8962b1c914c1633b386a2b3eaee8525476df2fa9e531e4d4ac61","last_reissued_at":"2026-05-18T00:23:42.109282Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:42.109282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sentence Boundary Detection for French with Subword-Level Information Vectors and Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carlos-Emiliano Gonz\\'alez-Gallardo, Juan-Manuel Torres-Moreno","submitted_at":"2018-02-13T11:04:07Z","abstract_excerpt":"In this work we tackle the problem of sentence boundary detection applied to French as a binary classification task (\"sentence boundary\" or \"not sentence boundary\"). We combine convolutional neural networks with subword-level information vectors, which are word embedding representations learned from Wikipedia that take advantage of the words morphology; so each word is represented as a bag of their character n-grams.\n  We decide to use a big written dataset (French Gigaword) instead of standard size transcriptions to train and evaluate the proposed architectures with the intention of using the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04559","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":"1802.04559","created_at":"2026-05-18T00:23:42.109400+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04559v1","created_at":"2026-05-18T00:23:42.109400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04559","created_at":"2026-05-18T00:23:42.109400+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBV6FXCJRKEW","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBV6FXCJRKEWFMOJ","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBV6FXCJ","created_at":"2026-05-18T12:32:33.847187+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/LBV6FXCJRKEWFMOJCTAWGOZYNI","json":"https://pith.science/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI.json","graph_json":"https://pith.science/api/pith-number/LBV6FXCJRKEWFMOJCTAWGOZYNI/graph.json","events_json":"https://pith.science/api/pith-number/LBV6FXCJRKEWFMOJCTAWGOZYNI/events.json","paper":"https://pith.science/paper/LBV6FXCJ"},"agent_actions":{"view_html":"https://pith.science/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI","download_json":"https://pith.science/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI.json","view_paper":"https://pith.science/paper/LBV6FXCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04559&json=true","fetch_graph":"https://pith.science/api/pith-number/LBV6FXCJRKEWFMOJCTAWGOZYNI/graph.json","fetch_events":"https://pith.science/api/pith-number/LBV6FXCJRKEWFMOJCTAWGOZYNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI/action/storage_attestation","attest_author":"https://pith.science/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI/action/author_attestation","sign_citation":"https://pith.science/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI/action/citation_signature","submit_replication":"https://pith.science/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI/action/replication_record"}},"created_at":"2026-05-18T00:23:42.109400+00:00","updated_at":"2026-05-18T00:23:42.109400+00:00"}