{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RG56VVUX5T7UH5CI5NN5N6FZ25","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"db8c7acde7cf56bf6ddb8ebd92049b44f2959b715827931bae6e22a5de6b0061","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-02T14:38:37Z","title_canon_sha256":"e1d9679089ba3c941ef1dcc9ebbc71f38a4675fb185ae64e6859997710e6b75a"},"schema_version":"1.0","source":{"id":"1904.01464","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.01464","created_at":"2026-05-17T23:41:53Z"},{"alias_kind":"arxiv_version","alias_value":"1904.01464v3","created_at":"2026-05-17T23:41:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01464","created_at":"2026-05-17T23:41:53Z"},{"alias_kind":"pith_short_12","alias_value":"RG56VVUX5T7U","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RG56VVUX5T7UH5CI","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RG56VVUX","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:0af7862986c24c347cbbd2cb8c08a612c0f906d8663025a4406703e5d688ae98","target":"graph","created_at":"2026-05-17T23:41:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Lemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form. Using context can help, both for unseen and ambiguous words. Yet most context-sensitive approaches require full lemma-annotated sentences for training, which may be scarce or unavailable in low-resource languages. In addition (as shown here), in a low-resource setting, a lemmatizer can learn more from $n$ labeled examples of distinct words (types) than from $n$ (contiguous) labeled tokens, since the latter contain far fewer distinct types. To combine the efficiency of type-bas","authors_text":"Sharon Goldwater, Toms Bergmanis","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-02T14:38:37Z","title":"Training Data Augmentation for Context-Sensitive Neural Lemmatization Using Inflection Tables and Raw Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01464","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bcc889a928104aa1287c9ad0fdd9701cc4f37cba0a83bba80cb44d3200aebc2d","target":"record","created_at":"2026-05-17T23:41:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"db8c7acde7cf56bf6ddb8ebd92049b44f2959b715827931bae6e22a5de6b0061","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-02T14:38:37Z","title_canon_sha256":"e1d9679089ba3c941ef1dcc9ebbc71f38a4675fb185ae64e6859997710e6b75a"},"schema_version":"1.0","source":{"id":"1904.01464","kind":"arxiv","version":3}},"canonical_sha256":"89bbead697ecff43f448eb5bd6f8b9d748e511c6709698edcccb759457821a40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89bbead697ecff43f448eb5bd6f8b9d748e511c6709698edcccb759457821a40","first_computed_at":"2026-05-17T23:41:53.212433Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:53.212433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"adGGlaSSzvw3KalVwkZhcKLP43MioqimASUFe6ldB12/5z6If5dJlU8LsA314yI7+lOHjSSCLoLw+RiJ/SWvBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:53.212891Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.01464","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcc889a928104aa1287c9ad0fdd9701cc4f37cba0a83bba80cb44d3200aebc2d","sha256:0af7862986c24c347cbbd2cb8c08a612c0f906d8663025a4406703e5d688ae98"],"state_sha256":"d3bdfe69e3e2f688f26ab014bd675cbadd09ff6aa75e43d5857da68bdf73c85f"}