{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:G6M7KFRFGORSNS6OAYJ46A4OSB","short_pith_number":"pith:G6M7KFRF","schema_version":"1.0","canonical_sha256":"3799f5162533a326cbce0613cf038e90643eb338eab5bce64261eddb3969d55d","source":{"kind":"arxiv","id":"1809.04259","version":1},"attestation_state":"computed","paper":{"title":"Generalizing Word Embeddings using Bag of Subwords","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jinman Zhao, Sidharth Mudgal, Yingyu Liang","submitted_at":"2018-09-12T05:15:32Z","abstract_excerpt":"We approach the problem of generalizing pre-trained word embeddings beyond fixed-size vocabularies without using additional contextual information. We propose a subword-level word vector generation model that views words as bags of character $n$-grams. The model is simple, fast to train and provides good vectors for rare or unseen words. Experiments show that our model achieves state-of-the-art performances in English word similarity task and in joint prediction of part-of-speech tag and morphosyntactic attributes in 23 languages, suggesting our model's ability in capturing the relationship be"},"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":"1809.04259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-12T05:15:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4e944a98fc7e1ad5fa61b8a88afcec3ad38c5c658c730e2a3c657cfccd290168","abstract_canon_sha256":"7eb7cb6bf2d717224cbf6ff5b254dd089b0c5762785ebbcb2a0af0ed539c88d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:52.973826Z","signature_b64":"aKf1BH0TrDw+iSVUJpCc29dKb6WeuhTBRWgYi8xVLugp8nGIPlRP/BrDP3yc30lFFabexldI6K0eLuhXIGbAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3799f5162533a326cbce0613cf038e90643eb338eab5bce64261eddb3969d55d","last_reissued_at":"2026-05-18T00:05:52.973274Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:52.973274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalizing Word Embeddings using Bag of Subwords","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jinman Zhao, Sidharth Mudgal, Yingyu Liang","submitted_at":"2018-09-12T05:15:32Z","abstract_excerpt":"We approach the problem of generalizing pre-trained word embeddings beyond fixed-size vocabularies without using additional contextual information. We propose a subword-level word vector generation model that views words as bags of character $n$-grams. The model is simple, fast to train and provides good vectors for rare or unseen words. Experiments show that our model achieves state-of-the-art performances in English word similarity task and in joint prediction of part-of-speech tag and morphosyntactic attributes in 23 languages, suggesting our model's ability in capturing the relationship be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04259","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":"1809.04259","created_at":"2026-05-18T00:05:52.973371+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.04259v1","created_at":"2026-05-18T00:05:52.973371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04259","created_at":"2026-05-18T00:05:52.973371+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6M7KFRFGORS","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6M7KFRFGORSNS6O","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6M7KFRF","created_at":"2026-05-18T12:32:25.280505+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/G6M7KFRFGORSNS6OAYJ46A4OSB","json":"https://pith.science/pith/G6M7KFRFGORSNS6OAYJ46A4OSB.json","graph_json":"https://pith.science/api/pith-number/G6M7KFRFGORSNS6OAYJ46A4OSB/graph.json","events_json":"https://pith.science/api/pith-number/G6M7KFRFGORSNS6OAYJ46A4OSB/events.json","paper":"https://pith.science/paper/G6M7KFRF"},"agent_actions":{"view_html":"https://pith.science/pith/G6M7KFRFGORSNS6OAYJ46A4OSB","download_json":"https://pith.science/pith/G6M7KFRFGORSNS6OAYJ46A4OSB.json","view_paper":"https://pith.science/paper/G6M7KFRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.04259&json=true","fetch_graph":"https://pith.science/api/pith-number/G6M7KFRFGORSNS6OAYJ46A4OSB/graph.json","fetch_events":"https://pith.science/api/pith-number/G6M7KFRFGORSNS6OAYJ46A4OSB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6M7KFRFGORSNS6OAYJ46A4OSB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6M7KFRFGORSNS6OAYJ46A4OSB/action/storage_attestation","attest_author":"https://pith.science/pith/G6M7KFRFGORSNS6OAYJ46A4OSB/action/author_attestation","sign_citation":"https://pith.science/pith/G6M7KFRFGORSNS6OAYJ46A4OSB/action/citation_signature","submit_replication":"https://pith.science/pith/G6M7KFRFGORSNS6OAYJ46A4OSB/action/replication_record"}},"created_at":"2026-05-18T00:05:52.973371+00:00","updated_at":"2026-05-18T00:05:52.973371+00:00"}