{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GUQPO24OHVTA7D7N5WYCVR4P5A","short_pith_number":"pith:GUQPO24O","schema_version":"1.0","canonical_sha256":"3520f76b8e3d660f8fededb02ac78fe812e056968d860d5525602d065dcf2a84","source":{"kind":"arxiv","id":"2105.01279","version":1},"attestation_state":"computed","paper":{"title":"ZEN 2.0: Continue Training and Adaption for N-gram Enhanced Text Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kai-Fu Lee, Tong Zhang, Yan Song, Yonggang Wang","submitted_at":"2021-05-04T04:08:58Z","abstract_excerpt":"Pre-trained text encoders have drawn sustaining attention in natural language processing (NLP) and shown their capability in obtaining promising results in different tasks. Recent studies illustrated that external self-supervised signals (or knowledge extracted by unsupervised learning, such as n-grams) are beneficial to provide useful semantic evidence for understanding languages such as Chinese, so as to improve the performance on various downstream tasks accordingly. To further enhance the encoders, in this paper, we propose to pre-train n-gram-enhanced encoders with a large volume of data "},"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":"2105.01279","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-04T04:08:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"510595a3011b6489ef96281b63f54ff019236b750c35b0b501275b1b3c8497da","abstract_canon_sha256":"d69ecd1e4b26a9e179b8e1ee59c6b76398543c1f16b425429caa4d6696886fc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:15.410117Z","signature_b64":"Sw2CyhF/1MwSiEgqYgsm17kqAVve804BDQKGqPVyEg+QOMnlutN+Z71RNHyMYeWisCrRJMbymTePEeULDn8jCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3520f76b8e3d660f8fededb02ac78fe812e056968d860d5525602d065dcf2a84","last_reissued_at":"2026-07-05T02:37:15.409554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:15.409554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZEN 2.0: Continue Training and Adaption for N-gram Enhanced Text Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kai-Fu Lee, Tong Zhang, Yan Song, Yonggang Wang","submitted_at":"2021-05-04T04:08:58Z","abstract_excerpt":"Pre-trained text encoders have drawn sustaining attention in natural language processing (NLP) and shown their capability in obtaining promising results in different tasks. Recent studies illustrated that external self-supervised signals (or knowledge extracted by unsupervised learning, such as n-grams) are beneficial to provide useful semantic evidence for understanding languages such as Chinese, so as to improve the performance on various downstream tasks accordingly. To further enhance the encoders, in this paper, we propose to pre-train n-gram-enhanced encoders with a large volume of data "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.01279","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2105.01279/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2105.01279","created_at":"2026-07-05T02:37:15.409649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.01279v1","created_at":"2026-07-05T02:37:15.409649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.01279","created_at":"2026-07-05T02:37:15.409649+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUQPO24OHVTA","created_at":"2026-07-05T02:37:15.409649+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUQPO24OHVTA7D7N","created_at":"2026-07-05T02:37:15.409649+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUQPO24O","created_at":"2026-07-05T02:37:15.409649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15275","citing_title":"ChiMed 2.0: Advancing Chinese Medical Dataset in Facilitating Large Language Modeling","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GUQPO24OHVTA7D7N5WYCVR4P5A","json":"https://pith.science/pith/GUQPO24OHVTA7D7N5WYCVR4P5A.json","graph_json":"https://pith.science/api/pith-number/GUQPO24OHVTA7D7N5WYCVR4P5A/graph.json","events_json":"https://pith.science/api/pith-number/GUQPO24OHVTA7D7N5WYCVR4P5A/events.json","paper":"https://pith.science/paper/GUQPO24O"},"agent_actions":{"view_html":"https://pith.science/pith/GUQPO24OHVTA7D7N5WYCVR4P5A","download_json":"https://pith.science/pith/GUQPO24OHVTA7D7N5WYCVR4P5A.json","view_paper":"https://pith.science/paper/GUQPO24O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.01279&json=true","fetch_graph":"https://pith.science/api/pith-number/GUQPO24OHVTA7D7N5WYCVR4P5A/graph.json","fetch_events":"https://pith.science/api/pith-number/GUQPO24OHVTA7D7N5WYCVR4P5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUQPO24OHVTA7D7N5WYCVR4P5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUQPO24OHVTA7D7N5WYCVR4P5A/action/storage_attestation","attest_author":"https://pith.science/pith/GUQPO24OHVTA7D7N5WYCVR4P5A/action/author_attestation","sign_citation":"https://pith.science/pith/GUQPO24OHVTA7D7N5WYCVR4P5A/action/citation_signature","submit_replication":"https://pith.science/pith/GUQPO24OHVTA7D7N5WYCVR4P5A/action/replication_record"}},"created_at":"2026-07-05T02:37:15.409649+00:00","updated_at":"2026-07-05T02:37:15.409649+00:00"}