{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QLEJK4DB5VKY37WVZJ6FL74XTE","short_pith_number":"pith:QLEJK4DB","schema_version":"1.0","canonical_sha256":"82c8957061ed558dfed5ca7c55ff9799106f180b6064abd518e408e0bfdd8f3b","source":{"kind":"arxiv","id":"1902.00972","version":2},"attestation_state":"computed","paper":{"title":"Universal Lemmatizer: A Sequence to Sequence Model for Lemmatizing Universal Dependencies Treebanks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Filip Ginter, Jenna Kanerva, Tapio Salakoski","submitted_at":"2019-02-03T21:38:29Z","abstract_excerpt":"In this paper we present a novel lemmatization method based on a sequence-to-sequence neural network architecture and morphosyntactic context representation. In the proposed method, our context-sensitive lemmatizer generates the lemma one character at a time based on the surface form characters and its morphosyntactic features obtained from a morphological tagger. We argue that a sliding window context representation suffers from sparseness, while in majority of cases the morphosyntactic features of a word bring enough information to resolve lemma ambiguities while keeping the context represen"},"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":"1902.00972","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-03T21:38:29Z","cross_cats_sorted":[],"title_canon_sha256":"1006990abf97ce12bbf6ef9988d6dc5dcfee20785332ae5a3b4b31d176531131","abstract_canon_sha256":"c3344c2f6c3dbf898e4a9a07f251a5427da0d06e6379d840485d25701469c216"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:55:16.493158Z","signature_b64":"5HsdIV2X0kGzKWptEAVT22OcYzZ1asprEwyAZYydZUxCyveYg2044cnEqhXk04vS2rC0H7tqv4tiYylkjbzRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82c8957061ed558dfed5ca7c55ff9799106f180b6064abd518e408e0bfdd8f3b","last_reissued_at":"2026-07-05T00:55:16.492676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:55:16.492676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Lemmatizer: A Sequence to Sequence Model for Lemmatizing Universal Dependencies Treebanks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Filip Ginter, Jenna Kanerva, Tapio Salakoski","submitted_at":"2019-02-03T21:38:29Z","abstract_excerpt":"In this paper we present a novel lemmatization method based on a sequence-to-sequence neural network architecture and morphosyntactic context representation. In the proposed method, our context-sensitive lemmatizer generates the lemma one character at a time based on the surface form characters and its morphosyntactic features obtained from a morphological tagger. We argue that a sliding window context representation suffers from sparseness, while in majority of cases the morphosyntactic features of a word bring enough information to resolve lemma ambiguities while keeping the context represen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00972","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1902.00972/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":"1902.00972","created_at":"2026-07-05T00:55:16.492732+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.00972v2","created_at":"2026-07-05T00:55:16.492732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00972","created_at":"2026-07-05T00:55:16.492732+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLEJK4DB5VKY","created_at":"2026-07-05T00:55:16.492732+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLEJK4DB5VKY37WV","created_at":"2026-07-05T00:55:16.492732+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLEJK4DB","created_at":"2026-07-05T00:55:16.492732+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/QLEJK4DB5VKY37WVZJ6FL74XTE","json":"https://pith.science/pith/QLEJK4DB5VKY37WVZJ6FL74XTE.json","graph_json":"https://pith.science/api/pith-number/QLEJK4DB5VKY37WVZJ6FL74XTE/graph.json","events_json":"https://pith.science/api/pith-number/QLEJK4DB5VKY37WVZJ6FL74XTE/events.json","paper":"https://pith.science/paper/QLEJK4DB"},"agent_actions":{"view_html":"https://pith.science/pith/QLEJK4DB5VKY37WVZJ6FL74XTE","download_json":"https://pith.science/pith/QLEJK4DB5VKY37WVZJ6FL74XTE.json","view_paper":"https://pith.science/paper/QLEJK4DB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.00972&json=true","fetch_graph":"https://pith.science/api/pith-number/QLEJK4DB5VKY37WVZJ6FL74XTE/graph.json","fetch_events":"https://pith.science/api/pith-number/QLEJK4DB5VKY37WVZJ6FL74XTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLEJK4DB5VKY37WVZJ6FL74XTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLEJK4DB5VKY37WVZJ6FL74XTE/action/storage_attestation","attest_author":"https://pith.science/pith/QLEJK4DB5VKY37WVZJ6FL74XTE/action/author_attestation","sign_citation":"https://pith.science/pith/QLEJK4DB5VKY37WVZJ6FL74XTE/action/citation_signature","submit_replication":"https://pith.science/pith/QLEJK4DB5VKY37WVZJ6FL74XTE/action/replication_record"}},"created_at":"2026-07-05T00:55:16.492732+00:00","updated_at":"2026-07-05T00:55:16.492732+00:00"}