{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GTIESEGTVC3GUZQ3UJ45BXUJ6T","short_pith_number":"pith:GTIESEGT","schema_version":"1.0","canonical_sha256":"34d04910d3a8b66a661ba279d0de89f4dad36927ee67c4fd6d2cff757fbdfd7c","source":{"kind":"arxiv","id":"1907.09038","version":1},"attestation_state":"computed","paper":{"title":"Augmenting a BiLSTM tagger with a Morphological Lexicon and a Lexical Category Identification Step","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hrafn Loftsson, \\\"Orvar K\\'arason, Stein{\\th}\\'or Steingr\\'imsson","submitted_at":"2019-07-21T21:27:44Z","abstract_excerpt":"Previous work on using BiLSTM models for PoS tagging has primarily focused on small tagsets. We evaluate BiLSTM models for tagging Icelandic, a morphologically rich language, using a relatively large tagset. Our baseline BiLSTM model achieves higher accuracy than any previously published tagger not taking advantage of a morphological lexicon. When we extend the model by incorporating such data, we outperform previous state-of-the-art results by a significant margin. We also report on work in progress that attempts to address the problem of data sparsity inherent in morphologically detailed, fi"},"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":"1907.09038","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-07-21T21:27:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"60c318edd23352ad6e1abe10c333f338b8f53b791cc59dd2958ee53b46e9a097","abstract_canon_sha256":"f049c493a553915e239b641c1f903e957969b8ae1c8677a86894756df9d7ec00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:02.336162Z","signature_b64":"TtBTODV6WElW02mcgipTowR0gCDWbpWdqUaCNSRC62VEdS8jb50W8Ej3Kj0+orCmAusYj2COyS19/+gFBVfvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34d04910d3a8b66a661ba279d0de89f4dad36927ee67c4fd6d2cff757fbdfd7c","last_reissued_at":"2026-05-17T23:40:02.335649Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:02.335649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Augmenting a BiLSTM tagger with a Morphological Lexicon and a Lexical Category Identification Step","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hrafn Loftsson, \\\"Orvar K\\'arason, Stein{\\th}\\'or Steingr\\'imsson","submitted_at":"2019-07-21T21:27:44Z","abstract_excerpt":"Previous work on using BiLSTM models for PoS tagging has primarily focused on small tagsets. We evaluate BiLSTM models for tagging Icelandic, a morphologically rich language, using a relatively large tagset. Our baseline BiLSTM model achieves higher accuracy than any previously published tagger not taking advantage of a morphological lexicon. When we extend the model by incorporating such data, we outperform previous state-of-the-art results by a significant margin. We also report on work in progress that attempts to address the problem of data sparsity inherent in morphologically detailed, fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.09038","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":"1907.09038","created_at":"2026-05-17T23:40:02.335735+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.09038v1","created_at":"2026-05-17T23:40:02.335735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.09038","created_at":"2026-05-17T23:40:02.335735+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTIESEGTVC3G","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTIESEGTVC3GUZQ3","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTIESEGT","created_at":"2026-05-18T12:33:18.533446+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/GTIESEGTVC3GUZQ3UJ45BXUJ6T","json":"https://pith.science/pith/GTIESEGTVC3GUZQ3UJ45BXUJ6T.json","graph_json":"https://pith.science/api/pith-number/GTIESEGTVC3GUZQ3UJ45BXUJ6T/graph.json","events_json":"https://pith.science/api/pith-number/GTIESEGTVC3GUZQ3UJ45BXUJ6T/events.json","paper":"https://pith.science/paper/GTIESEGT"},"agent_actions":{"view_html":"https://pith.science/pith/GTIESEGTVC3GUZQ3UJ45BXUJ6T","download_json":"https://pith.science/pith/GTIESEGTVC3GUZQ3UJ45BXUJ6T.json","view_paper":"https://pith.science/paper/GTIESEGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.09038&json=true","fetch_graph":"https://pith.science/api/pith-number/GTIESEGTVC3GUZQ3UJ45BXUJ6T/graph.json","fetch_events":"https://pith.science/api/pith-number/GTIESEGTVC3GUZQ3UJ45BXUJ6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTIESEGTVC3GUZQ3UJ45BXUJ6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTIESEGTVC3GUZQ3UJ45BXUJ6T/action/storage_attestation","attest_author":"https://pith.science/pith/GTIESEGTVC3GUZQ3UJ45BXUJ6T/action/author_attestation","sign_citation":"https://pith.science/pith/GTIESEGTVC3GUZQ3UJ45BXUJ6T/action/citation_signature","submit_replication":"https://pith.science/pith/GTIESEGTVC3GUZQ3UJ45BXUJ6T/action/replication_record"}},"created_at":"2026-05-17T23:40:02.335735+00:00","updated_at":"2026-05-17T23:40:02.335735+00:00"}