{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:BHRB6NO463A7OMK66TCM37GTVK","short_pith_number":"pith:BHRB6NO4","schema_version":"1.0","canonical_sha256":"09e21f35dcf6c1f7315ef4c4cdfcd3aa98df8a6905b1b378e4023dc7d9acf8f6","source":{"kind":"arxiv","id":"1504.06650","version":1},"attestation_state":"computed","paper":{"title":"Learning Dictionaries for Named Entity Recognition using Minimal Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Arvind Neelakantan, Michael Collins","submitted_at":"2015-04-24T21:43:55Z","abstract_excerpt":"This paper describes an approach for automatic construction of dictionaries for Named Entity Recognition (NER) using large amounts of unlabeled data and a few seed examples. We use Canonical Correlation Analysis (CCA) to obtain lower dimensional embeddings (representations) for candidate phrases and classify these phrases using a small number of labeled examples. Our method achieves 16.5% and 11.3% F-1 score improvement over co-training on disease and virus NER respectively. We also show that by adding candidate phrase embeddings as features in a sequence tagger gives better performance compar"},"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":"1504.06650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-04-24T21:43:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f4e45ce5b5f454a08d1f98301117af4b3445b270f9ca9c2ca4c66208c314098e","abstract_canon_sha256":"ca5b374f0ebf1313845253a279896ee9ced4c97151f25bc6d667e9fa4e95029d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:17:52.884047Z","signature_b64":"ct8gfvJ+kSZoonUAn2Q9s4NidwA7GeuN8bRAY4+B33VDeND9U181tjd6eBf1BAyPHuTdS6l1YyGTeZqp836FDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09e21f35dcf6c1f7315ef4c4cdfcd3aa98df8a6905b1b378e4023dc7d9acf8f6","last_reissued_at":"2026-05-18T02:17:52.883432Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:17:52.883432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Dictionaries for Named Entity Recognition using Minimal Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Arvind Neelakantan, Michael Collins","submitted_at":"2015-04-24T21:43:55Z","abstract_excerpt":"This paper describes an approach for automatic construction of dictionaries for Named Entity Recognition (NER) using large amounts of unlabeled data and a few seed examples. We use Canonical Correlation Analysis (CCA) to obtain lower dimensional embeddings (representations) for candidate phrases and classify these phrases using a small number of labeled examples. Our method achieves 16.5% and 11.3% F-1 score improvement over co-training on disease and virus NER respectively. We also show that by adding candidate phrase embeddings as features in a sequence tagger gives better performance compar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.06650","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":"1504.06650","created_at":"2026-05-18T02:17:52.883539+00:00"},{"alias_kind":"arxiv_version","alias_value":"1504.06650v1","created_at":"2026-05-18T02:17:52.883539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.06650","created_at":"2026-05-18T02:17:52.883539+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHRB6NO463A7","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHRB6NO463A7OMK6","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHRB6NO4","created_at":"2026-05-18T12:29:14.074870+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/BHRB6NO463A7OMK66TCM37GTVK","json":"https://pith.science/pith/BHRB6NO463A7OMK66TCM37GTVK.json","graph_json":"https://pith.science/api/pith-number/BHRB6NO463A7OMK66TCM37GTVK/graph.json","events_json":"https://pith.science/api/pith-number/BHRB6NO463A7OMK66TCM37GTVK/events.json","paper":"https://pith.science/paper/BHRB6NO4"},"agent_actions":{"view_html":"https://pith.science/pith/BHRB6NO463A7OMK66TCM37GTVK","download_json":"https://pith.science/pith/BHRB6NO463A7OMK66TCM37GTVK.json","view_paper":"https://pith.science/paper/BHRB6NO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1504.06650&json=true","fetch_graph":"https://pith.science/api/pith-number/BHRB6NO463A7OMK66TCM37GTVK/graph.json","fetch_events":"https://pith.science/api/pith-number/BHRB6NO463A7OMK66TCM37GTVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHRB6NO463A7OMK66TCM37GTVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHRB6NO463A7OMK66TCM37GTVK/action/storage_attestation","attest_author":"https://pith.science/pith/BHRB6NO463A7OMK66TCM37GTVK/action/author_attestation","sign_citation":"https://pith.science/pith/BHRB6NO463A7OMK66TCM37GTVK/action/citation_signature","submit_replication":"https://pith.science/pith/BHRB6NO463A7OMK66TCM37GTVK/action/replication_record"}},"created_at":"2026-05-18T02:17:52.883539+00:00","updated_at":"2026-05-18T02:17:52.883539+00:00"}