{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:2EMU7SCBMOJGYYLWW5QTLXLZOZ","short_pith_number":"pith:2EMU7SCB","schema_version":"1.0","canonical_sha256":"d1194fc84163926c6176b76135dd79764d00cd81b4da8ad60afbba4fe92af19f","source":{"kind":"arxiv","id":"1305.5918","version":1},"attestation_state":"computed","paper":{"title":"Reduce Meaningless Words for Joint Chinese Word Segmentation and Part-of-speech Tagging","license":"http://creativecommons.org/licenses/by/3.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kaixu Zhang, Maosong Sun","submitted_at":"2013-05-25T13:20:31Z","abstract_excerpt":"Conventional statistics-based methods for joint Chinese word segmentation and part-of-speech tagging (S&T) have generalization ability to recognize new words that do not appear in the training data. An undesirable side effect is that a number of meaningless words will be incorrectly created. We propose an effective and efficient framework for S&T that introduces features to significantly reduce meaningless words generation. A general lexicon, Wikepedia and a large-scale raw corpus of 200 billion characters are used to generate word-based features for the wordhood. The word-lattice based framew"},"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":"1305.5918","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.CL","submitted_at":"2013-05-25T13:20:31Z","cross_cats_sorted":[],"title_canon_sha256":"bf9cffde812cf6ddc73107191741e7e1b978761ef0a0249eae2f89745845816c","abstract_canon_sha256":"cbd5dac193aa3d50214ad3a4969c76fd16b9560b75e412945f9eca974e95ec38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:24:53.343960Z","signature_b64":"zAOxbCXAMlJUcN0wDc+dC5vjhuLm4cFn/Zydw8Qbe7EUvclfJBNLXxcZCOelFjaMXfVEcqQ5oEwW6fag1yw/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1194fc84163926c6176b76135dd79764d00cd81b4da8ad60afbba4fe92af19f","last_reissued_at":"2026-05-18T03:24:53.343301Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:24:53.343301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reduce Meaningless Words for Joint Chinese Word Segmentation and Part-of-speech Tagging","license":"http://creativecommons.org/licenses/by/3.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kaixu Zhang, Maosong Sun","submitted_at":"2013-05-25T13:20:31Z","abstract_excerpt":"Conventional statistics-based methods for joint Chinese word segmentation and part-of-speech tagging (S&T) have generalization ability to recognize new words that do not appear in the training data. An undesirable side effect is that a number of meaningless words will be incorrectly created. We propose an effective and efficient framework for S&T that introduces features to significantly reduce meaningless words generation. A general lexicon, Wikepedia and a large-scale raw corpus of 200 billion characters are used to generate word-based features for the wordhood. The word-lattice based framew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1305.5918","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":"1305.5918","created_at":"2026-05-18T03:24:53.343397+00:00"},{"alias_kind":"arxiv_version","alias_value":"1305.5918v1","created_at":"2026-05-18T03:24:53.343397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.5918","created_at":"2026-05-18T03:24:53.343397+00:00"},{"alias_kind":"pith_short_12","alias_value":"2EMU7SCBMOJG","created_at":"2026-05-18T12:27:30.460161+00:00"},{"alias_kind":"pith_short_16","alias_value":"2EMU7SCBMOJGYYLW","created_at":"2026-05-18T12:27:30.460161+00:00"},{"alias_kind":"pith_short_8","alias_value":"2EMU7SCB","created_at":"2026-05-18T12:27:30.460161+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/2EMU7SCBMOJGYYLWW5QTLXLZOZ","json":"https://pith.science/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ.json","graph_json":"https://pith.science/api/pith-number/2EMU7SCBMOJGYYLWW5QTLXLZOZ/graph.json","events_json":"https://pith.science/api/pith-number/2EMU7SCBMOJGYYLWW5QTLXLZOZ/events.json","paper":"https://pith.science/paper/2EMU7SCB"},"agent_actions":{"view_html":"https://pith.science/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ","download_json":"https://pith.science/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ.json","view_paper":"https://pith.science/paper/2EMU7SCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1305.5918&json=true","fetch_graph":"https://pith.science/api/pith-number/2EMU7SCBMOJGYYLWW5QTLXLZOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2EMU7SCBMOJGYYLWW5QTLXLZOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ/action/storage_attestation","attest_author":"https://pith.science/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ/action/author_attestation","sign_citation":"https://pith.science/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ/action/citation_signature","submit_replication":"https://pith.science/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ/action/replication_record"}},"created_at":"2026-05-18T03:24:53.343397+00:00","updated_at":"2026-05-18T03:24:53.343397+00:00"}