{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VGMAKBE7OV7PUZIO3WMBXT4MTH","short_pith_number":"pith:VGMAKBE7","schema_version":"1.0","canonical_sha256":"a99805049f757efa650edd981bcf8c99e05dd13c357b9e935de026771131f134","source":{"kind":"arxiv","id":"1704.02813","version":1},"attestation_state":"computed","paper":{"title":"Character-Word LSTM Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hugo Van hamme, Joris Pelemans, Lyan Verwimp, Patrick Wambacq","submitted_at":"2017-04-10T11:42:09Z","abstract_excerpt":"We present a Character-Word Long Short-Term Memory Language Model which both reduces the perplexity with respect to a baseline word-level language model and reduces the number of parameters of the model. Character information can reveal structural (dis)similarities between words and can even be used when a word is out-of-vocabulary, thus improving the modeling of infrequent and unknown words. By concatenating word and character embeddings, we achieve up to 2.77% relative improvement on English compared to a baseline model with a similar amount of parameters and 4.57% on Dutch. Moreover, we als"},"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":"1704.02813","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-04-10T11:42:09Z","cross_cats_sorted":[],"title_canon_sha256":"65e15e2de706f1b983bee4517f2e826ee21ddc9329ac83d69afeb9a278bf19ae","abstract_canon_sha256":"6d9d6650574b47aec83565603788589791313646b79e82acb39b43d357d6f222"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:44.345089Z","signature_b64":"vrEQPn6Df2JaSF6NI2eCEEGhC0QoSY0aOT70Y2+KiJpSwjh51qZN0ZrqiN76eJ5WD8Xsy+ERO679c8lW3uIYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a99805049f757efa650edd981bcf8c99e05dd13c357b9e935de026771131f134","last_reissued_at":"2026-05-18T00:46:44.344446Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:44.344446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Character-Word LSTM Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hugo Van hamme, Joris Pelemans, Lyan Verwimp, Patrick Wambacq","submitted_at":"2017-04-10T11:42:09Z","abstract_excerpt":"We present a Character-Word Long Short-Term Memory Language Model which both reduces the perplexity with respect to a baseline word-level language model and reduces the number of parameters of the model. Character information can reveal structural (dis)similarities between words and can even be used when a word is out-of-vocabulary, thus improving the modeling of infrequent and unknown words. By concatenating word and character embeddings, we achieve up to 2.77% relative improvement on English compared to a baseline model with a similar amount of parameters and 4.57% on Dutch. Moreover, we als"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.02813","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":"1704.02813","created_at":"2026-05-18T00:46:44.344524+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.02813v1","created_at":"2026-05-18T00:46:44.344524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.02813","created_at":"2026-05-18T00:46:44.344524+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGMAKBE7OV7P","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGMAKBE7OV7PUZIO","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGMAKBE7","created_at":"2026-05-18T12:31:49.984773+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/VGMAKBE7OV7PUZIO3WMBXT4MTH","json":"https://pith.science/pith/VGMAKBE7OV7PUZIO3WMBXT4MTH.json","graph_json":"https://pith.science/api/pith-number/VGMAKBE7OV7PUZIO3WMBXT4MTH/graph.json","events_json":"https://pith.science/api/pith-number/VGMAKBE7OV7PUZIO3WMBXT4MTH/events.json","paper":"https://pith.science/paper/VGMAKBE7"},"agent_actions":{"view_html":"https://pith.science/pith/VGMAKBE7OV7PUZIO3WMBXT4MTH","download_json":"https://pith.science/pith/VGMAKBE7OV7PUZIO3WMBXT4MTH.json","view_paper":"https://pith.science/paper/VGMAKBE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.02813&json=true","fetch_graph":"https://pith.science/api/pith-number/VGMAKBE7OV7PUZIO3WMBXT4MTH/graph.json","fetch_events":"https://pith.science/api/pith-number/VGMAKBE7OV7PUZIO3WMBXT4MTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGMAKBE7OV7PUZIO3WMBXT4MTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGMAKBE7OV7PUZIO3WMBXT4MTH/action/storage_attestation","attest_author":"https://pith.science/pith/VGMAKBE7OV7PUZIO3WMBXT4MTH/action/author_attestation","sign_citation":"https://pith.science/pith/VGMAKBE7OV7PUZIO3WMBXT4MTH/action/citation_signature","submit_replication":"https://pith.science/pith/VGMAKBE7OV7PUZIO3WMBXT4MTH/action/replication_record"}},"created_at":"2026-05-18T00:46:44.344524+00:00","updated_at":"2026-05-18T00:46:44.344524+00:00"}