{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2W2ZY64GWAU73OXFL3VF2M4KA4","short_pith_number":"pith:2W2ZY64G","schema_version":"1.0","canonical_sha256":"d5b59c7b86b029fdbae55eea5d338a0715b0b60c67988ec90d46fe98d0348a5d","source":{"kind":"arxiv","id":"1910.02586","version":2},"attestation_state":"computed","paper":{"title":"Why Attention? Analyzing and Remedying BiLSTM Deficiency in Modeling Cross-Context for NER","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Peng-Hsuan Li, Tsu-Jui Fu, Wei-Yun Ma","submitted_at":"2019-10-07T03:03:08Z","abstract_excerpt":"State-of-the-art approaches of NER have used sequence-labeling BiLSTM as a core module. This paper formally shows the limitation of BiLSTM in modeling cross-context patterns. Two types of simple cross-structures -- self-attention and Cross-BiLSTM -- are shown to effectively remedy the problem. On both OntoNotes 5.0 and WNUT 2017, clear and consistent improvements are achieved over bare-bone models, up to 8.7% on some of the multi-token mentions. In-depth analyses across several aspects of the improvements, especially the identification of multi-token mentions, are further given."},"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":"1910.02586","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-07T03:03:08Z","cross_cats_sorted":[],"title_canon_sha256":"b098afbe4b0e7a6d0073398f4d685af3da688ad86f6b59ba666d91908990aa2b","abstract_canon_sha256":"a17c90197647426c7bab54b166dd1389769f50273c3ac026a93503a4921b8693"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:40.606677Z","signature_b64":"1BW40Wt/CiZZQiyjgJUx8HvQ8ijeL2eaOWuSpp43Z8N6Zk+I1zNb7TvMiFdYk0AJJtCviumtndW2JZEw1ToRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5b59c7b86b029fdbae55eea5d338a0715b0b60c67988ec90d46fe98d0348a5d","last_reissued_at":"2026-07-05T00:44:40.606262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:40.606262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Why Attention? Analyzing and Remedying BiLSTM Deficiency in Modeling Cross-Context for NER","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Peng-Hsuan Li, Tsu-Jui Fu, Wei-Yun Ma","submitted_at":"2019-10-07T03:03:08Z","abstract_excerpt":"State-of-the-art approaches of NER have used sequence-labeling BiLSTM as a core module. This paper formally shows the limitation of BiLSTM in modeling cross-context patterns. Two types of simple cross-structures -- self-attention and Cross-BiLSTM -- are shown to effectively remedy the problem. On both OntoNotes 5.0 and WNUT 2017, clear and consistent improvements are achieved over bare-bone models, up to 8.7% on some of the multi-token mentions. In-depth analyses across several aspects of the improvements, especially the identification of multi-token mentions, are further given."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.02586","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/1910.02586/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":"1910.02586","created_at":"2026-07-05T00:44:40.606323+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.02586v2","created_at":"2026-07-05T00:44:40.606323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.02586","created_at":"2026-07-05T00:44:40.606323+00:00"},{"alias_kind":"pith_short_12","alias_value":"2W2ZY64GWAU7","created_at":"2026-07-05T00:44:40.606323+00:00"},{"alias_kind":"pith_short_16","alias_value":"2W2ZY64GWAU73OXF","created_at":"2026-07-05T00:44:40.606323+00:00"},{"alias_kind":"pith_short_8","alias_value":"2W2ZY64G","created_at":"2026-07-05T00:44:40.606323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02057","citing_title":"Enhancing Speech Instruction Understanding and Disambiguation in Robotics via Speech Prosody","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2W2ZY64GWAU73OXFL3VF2M4KA4","json":"https://pith.science/pith/2W2ZY64GWAU73OXFL3VF2M4KA4.json","graph_json":"https://pith.science/api/pith-number/2W2ZY64GWAU73OXFL3VF2M4KA4/graph.json","events_json":"https://pith.science/api/pith-number/2W2ZY64GWAU73OXFL3VF2M4KA4/events.json","paper":"https://pith.science/paper/2W2ZY64G"},"agent_actions":{"view_html":"https://pith.science/pith/2W2ZY64GWAU73OXFL3VF2M4KA4","download_json":"https://pith.science/pith/2W2ZY64GWAU73OXFL3VF2M4KA4.json","view_paper":"https://pith.science/paper/2W2ZY64G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.02586&json=true","fetch_graph":"https://pith.science/api/pith-number/2W2ZY64GWAU73OXFL3VF2M4KA4/graph.json","fetch_events":"https://pith.science/api/pith-number/2W2ZY64GWAU73OXFL3VF2M4KA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2W2ZY64GWAU73OXFL3VF2M4KA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2W2ZY64GWAU73OXFL3VF2M4KA4/action/storage_attestation","attest_author":"https://pith.science/pith/2W2ZY64GWAU73OXFL3VF2M4KA4/action/author_attestation","sign_citation":"https://pith.science/pith/2W2ZY64GWAU73OXFL3VF2M4KA4/action/citation_signature","submit_replication":"https://pith.science/pith/2W2ZY64GWAU73OXFL3VF2M4KA4/action/replication_record"}},"created_at":"2026-07-05T00:44:40.606323+00:00","updated_at":"2026-07-05T00:44:40.606323+00:00"}