{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:1995:JJDIIP7YVZVWMQY74L6PINDMMQ","short_pith_number":"pith:JJDIIP7Y","schema_version":"1.0","canonical_sha256":"4a46843ff8ae6b66431fe2fcf4346c6425381a56db81e64541180433ae5be76d","source":{"kind":"arxiv","id":"cmp-lg/9502012","version":2},"attestation_state":"computed","paper":{"title":"A syntax-based part-of-speech analyser","license":"","headline":"","cross_cats":["cs.CL"],"primary_cat":"cmp-lg","authors_text":"Atro Voutilainen (Research Unit for Multilingual Language Technology, Finland), University of Helsinki","submitted_at":"1995-02-13T13:17:20Z","abstract_excerpt":"There are two main methodologies for constructing the knowledge base of a natural language analyser: the linguistic and the data-driven. Recent state-of-the-art part-of-speech taggers are based on the data-driven approach. Because of the known feasibility of the linguistic rule-based approach at related levels of description, the success of the data-driven approach in part-of-speech analysis may appear surprising. In this paper, a case is made for the syntactic nature of part-of-speech tagging. A new tagger of English that uses only linguistic distributional rules is outlined and empirically e"},"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":"cmp-lg/9502012","kind":"arxiv","version":2},"metadata":{"license":"","primary_cat":"cmp-lg","submitted_at":"1995-02-13T13:17:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fe222c2a5de8d9fe4a6a48b6244c7d4ef78f8be52813b78552ecda881cb06a50","abstract_canon_sha256":"c2732f77c8eb98d685bfb0d1bacf8b835798a3f685a9c18153e1c5757b4ffcc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:07:24.180932Z","signature_b64":"G8Gfm3YpxGhlUx8S3gKnEL9tlVS4cw/A5aTMQN375zkwiqZEodHQtztFKTl2P81B4JQ8HOhHx5RNP8l0MRINDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a46843ff8ae6b66431fe2fcf4346c6425381a56db81e64541180433ae5be76d","last_reissued_at":"2026-05-18T01:07:24.180473Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:07:24.180473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A syntax-based part-of-speech analyser","license":"","headline":"","cross_cats":["cs.CL"],"primary_cat":"cmp-lg","authors_text":"Atro Voutilainen (Research Unit for Multilingual Language Technology, Finland), University of Helsinki","submitted_at":"1995-02-13T13:17:20Z","abstract_excerpt":"There are two main methodologies for constructing the knowledge base of a natural language analyser: the linguistic and the data-driven. Recent state-of-the-art part-of-speech taggers are based on the data-driven approach. Because of the known feasibility of the linguistic rule-based approach at related levels of description, the success of the data-driven approach in part-of-speech analysis may appear surprising. In this paper, a case is made for the syntactic nature of part-of-speech tagging. A new tagger of English that uses only linguistic distributional rules is outlined and empirically e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cmp-lg/9502012","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":"cmp-lg/9502012","created_at":"2026-05-18T01:07:24.180544+00:00"},{"alias_kind":"arxiv_version","alias_value":"cmp-lg/9502012v2","created_at":"2026-05-18T01:07:24.180544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cmp-lg/9502012","created_at":"2026-05-18T01:07:24.180544+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJDIIP7YVZVW","created_at":"2026-05-18T12:25:47.700082+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJDIIP7YVZVWMQY7","created_at":"2026-05-18T12:25:47.700082+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJDIIP7Y","created_at":"2026-05-18T12:25:47.700082+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/JJDIIP7YVZVWMQY74L6PINDMMQ","json":"https://pith.science/pith/JJDIIP7YVZVWMQY74L6PINDMMQ.json","graph_json":"https://pith.science/api/pith-number/JJDIIP7YVZVWMQY74L6PINDMMQ/graph.json","events_json":"https://pith.science/api/pith-number/JJDIIP7YVZVWMQY74L6PINDMMQ/events.json","paper":"https://pith.science/paper/JJDIIP7Y"},"agent_actions":{"view_html":"https://pith.science/pith/JJDIIP7YVZVWMQY74L6PINDMMQ","download_json":"https://pith.science/pith/JJDIIP7YVZVWMQY74L6PINDMMQ.json","view_paper":"https://pith.science/paper/JJDIIP7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cmp-lg/9502012&json=true","fetch_graph":"https://pith.science/api/pith-number/JJDIIP7YVZVWMQY74L6PINDMMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JJDIIP7YVZVWMQY74L6PINDMMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJDIIP7YVZVWMQY74L6PINDMMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJDIIP7YVZVWMQY74L6PINDMMQ/action/storage_attestation","attest_author":"https://pith.science/pith/JJDIIP7YVZVWMQY74L6PINDMMQ/action/author_attestation","sign_citation":"https://pith.science/pith/JJDIIP7YVZVWMQY74L6PINDMMQ/action/citation_signature","submit_replication":"https://pith.science/pith/JJDIIP7YVZVWMQY74L6PINDMMQ/action/replication_record"}},"created_at":"2026-05-18T01:07:24.180544+00:00","updated_at":"2026-05-18T01:07:24.180544+00:00"}