{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FNBLOU6T5NZ5FN4KTWO4F3IOQ5","short_pith_number":"pith:FNBLOU6T","schema_version":"1.0","canonical_sha256":"2b42b753d3eb73d2b78a9d9dc2ed0e876faf83429fc852fe04580858372ebb4a","source":{"kind":"arxiv","id":"1708.04755","version":1},"attestation_state":"computed","paper":{"title":"Learning Chinese Word Representations From Glyphs Of Characters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hung-yi Lee, Tzu-Ray Su","submitted_at":"2017-08-16T03:17:57Z","abstract_excerpt":"In this paper, we propose new methods to learn Chinese word representations. Chinese characters are composed of graphical components, which carry rich semantics. It is common for a Chinese learner to comprehend the meaning of a word from these graphical components. As a result, we propose models that enhance word representations by character glyphs. The character glyph features are directly learned from the bitmaps of characters by convolutional auto-encoder(convAE), and the glyph features improve Chinese word representations which are already enhanced by character embeddings. Another contribu"},"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":"1708.04755","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-08-16T03:17:57Z","cross_cats_sorted":[],"title_canon_sha256":"9fc9720ed3dfa796e4a3c4c9069702a378eacfc0983f92f82b9ccb74792117c0","abstract_canon_sha256":"c7d8701d490b569bc55f5dfeae26e2b94ea520a0b481007d930a449fb8e7209e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:57.993165Z","signature_b64":"expR5vwBOdVGKXk3bVyPe04uJN31HCatZNmr/Xy8HW+cKFLqJ1V6L22pHTqL3bW/A2nZDf6d4B8CiCIeoibsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b42b753d3eb73d2b78a9d9dc2ed0e876faf83429fc852fe04580858372ebb4a","last_reissued_at":"2026-05-18T00:37:57.992636Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:57.992636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Chinese Word Representations From Glyphs Of Characters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hung-yi Lee, Tzu-Ray Su","submitted_at":"2017-08-16T03:17:57Z","abstract_excerpt":"In this paper, we propose new methods to learn Chinese word representations. Chinese characters are composed of graphical components, which carry rich semantics. It is common for a Chinese learner to comprehend the meaning of a word from these graphical components. As a result, we propose models that enhance word representations by character glyphs. The character glyph features are directly learned from the bitmaps of characters by convolutional auto-encoder(convAE), and the glyph features improve Chinese word representations which are already enhanced by character embeddings. Another contribu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.04755","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":"1708.04755","created_at":"2026-05-18T00:37:57.992725+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.04755v1","created_at":"2026-05-18T00:37:57.992725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04755","created_at":"2026-05-18T00:37:57.992725+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNBLOU6T5NZ5","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNBLOU6T5NZ5FN4K","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNBLOU6T","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24341","citing_title":"Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNBLOU6T5NZ5FN4KTWO4F3IOQ5","json":"https://pith.science/pith/FNBLOU6T5NZ5FN4KTWO4F3IOQ5.json","graph_json":"https://pith.science/api/pith-number/FNBLOU6T5NZ5FN4KTWO4F3IOQ5/graph.json","events_json":"https://pith.science/api/pith-number/FNBLOU6T5NZ5FN4KTWO4F3IOQ5/events.json","paper":"https://pith.science/paper/FNBLOU6T"},"agent_actions":{"view_html":"https://pith.science/pith/FNBLOU6T5NZ5FN4KTWO4F3IOQ5","download_json":"https://pith.science/pith/FNBLOU6T5NZ5FN4KTWO4F3IOQ5.json","view_paper":"https://pith.science/paper/FNBLOU6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.04755&json=true","fetch_graph":"https://pith.science/api/pith-number/FNBLOU6T5NZ5FN4KTWO4F3IOQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/FNBLOU6T5NZ5FN4KTWO4F3IOQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNBLOU6T5NZ5FN4KTWO4F3IOQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNBLOU6T5NZ5FN4KTWO4F3IOQ5/action/storage_attestation","attest_author":"https://pith.science/pith/FNBLOU6T5NZ5FN4KTWO4F3IOQ5/action/author_attestation","sign_citation":"https://pith.science/pith/FNBLOU6T5NZ5FN4KTWO4F3IOQ5/action/citation_signature","submit_replication":"https://pith.science/pith/FNBLOU6T5NZ5FN4KTWO4F3IOQ5/action/replication_record"}},"created_at":"2026-05-18T00:37:57.992725+00:00","updated_at":"2026-05-18T00:37:57.992725+00:00"}