{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GU3O2IZXCPRG4E34HA2TKCNYNY","short_pith_number":"pith:GU3O2IZX","schema_version":"1.0","canonical_sha256":"3536ed233713e26e137c38353509b86e100ffe5d81968a191aa1eadfb1a1f515","source":{"kind":"arxiv","id":"1902.08795","version":2},"attestation_state":"computed","paper":{"title":"VCWE: Visual Character-Enhanced Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chi Sun, Xipeng Qiu, Xuanjing Huang","submitted_at":"2019-02-23T14:25:51Z","abstract_excerpt":"Chinese is a logographic writing system, and the shape of Chinese characters contain rich syntactic and semantic information. In this paper, we propose a model to learn Chinese word embeddings via three-level composition: (1) a convolutional neural network to extract the intra-character compositionality from the visual shape of a character; (2) a recurrent neural network with self-attention to compose character representation into word embeddings; (3) the Skip-Gram framework to capture non-compositionality directly from the contextual information. Evaluations demonstrate the superior performan"},"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":"1902.08795","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T14:25:51Z","cross_cats_sorted":[],"title_canon_sha256":"697b589683c8c3069c8051b2e13f4347fadce09b7c6630e0caca3c4fec151587","abstract_canon_sha256":"9ba4019387790d9b159863ec1bb2b16fa450f2c3b8b2ea82808e09aaa5d00fb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:33.230744Z","signature_b64":"wvoXU6h0DsSG+Qsd8mHqkImTRUdPYNSy3bGXYlf3SZxA7cV+D5nsQQzlttXcl6xycF1l4spJgg3cbW/Q2SdHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3536ed233713e26e137c38353509b86e100ffe5d81968a191aa1eadfb1a1f515","last_reissued_at":"2026-05-17T23:50:33.230097Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:33.230097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VCWE: Visual Character-Enhanced Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chi Sun, Xipeng Qiu, Xuanjing Huang","submitted_at":"2019-02-23T14:25:51Z","abstract_excerpt":"Chinese is a logographic writing system, and the shape of Chinese characters contain rich syntactic and semantic information. In this paper, we propose a model to learn Chinese word embeddings via three-level composition: (1) a convolutional neural network to extract the intra-character compositionality from the visual shape of a character; (2) a recurrent neural network with self-attention to compose character representation into word embeddings; (3) the Skip-Gram framework to capture non-compositionality directly from the contextual information. Evaluations demonstrate the superior performan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08795","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":"1902.08795","created_at":"2026-05-17T23:50:33.230203+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.08795v2","created_at":"2026-05-17T23:50:33.230203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08795","created_at":"2026-05-17T23:50:33.230203+00:00"},{"alias_kind":"pith_short_12","alias_value":"GU3O2IZXCPRG","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"GU3O2IZXCPRG4E34","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"GU3O2IZX","created_at":"2026-05-18T12:33:18.533446+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/GU3O2IZXCPRG4E34HA2TKCNYNY","json":"https://pith.science/pith/GU3O2IZXCPRG4E34HA2TKCNYNY.json","graph_json":"https://pith.science/api/pith-number/GU3O2IZXCPRG4E34HA2TKCNYNY/graph.json","events_json":"https://pith.science/api/pith-number/GU3O2IZXCPRG4E34HA2TKCNYNY/events.json","paper":"https://pith.science/paper/GU3O2IZX"},"agent_actions":{"view_html":"https://pith.science/pith/GU3O2IZXCPRG4E34HA2TKCNYNY","download_json":"https://pith.science/pith/GU3O2IZXCPRG4E34HA2TKCNYNY.json","view_paper":"https://pith.science/paper/GU3O2IZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.08795&json=true","fetch_graph":"https://pith.science/api/pith-number/GU3O2IZXCPRG4E34HA2TKCNYNY/graph.json","fetch_events":"https://pith.science/api/pith-number/GU3O2IZXCPRG4E34HA2TKCNYNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GU3O2IZXCPRG4E34HA2TKCNYNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GU3O2IZXCPRG4E34HA2TKCNYNY/action/storage_attestation","attest_author":"https://pith.science/pith/GU3O2IZXCPRG4E34HA2TKCNYNY/action/author_attestation","sign_citation":"https://pith.science/pith/GU3O2IZXCPRG4E34HA2TKCNYNY/action/citation_signature","submit_replication":"https://pith.science/pith/GU3O2IZXCPRG4E34HA2TKCNYNY/action/replication_record"}},"created_at":"2026-05-17T23:50:33.230203+00:00","updated_at":"2026-05-17T23:50:33.230203+00:00"}