{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GMX4RAMFJHRGM43RIAEPQ7QMHY","short_pith_number":"pith:GMX4RAMF","schema_version":"1.0","canonical_sha256":"332fc8818549e26673714008f87e0c3e30c31527fecbc7f1e286b872889add9a","source":{"kind":"arxiv","id":"1904.00585","version":2},"attestation_state":"computed","paper":{"title":"Using Similarity Measures to Select Pretraining Data for NER","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ben Hachey, Cecile Paris, Sarvnaz Karimi, Xiang Dai","submitted_at":"2019-04-01T06:45:45Z","abstract_excerpt":"Word vectors and Language Models (LMs) pretrained on a large amount of unlabelled data can dramatically improve various Natural Language Processing (NLP) tasks. However, the measure and impact of similarity between pretraining data and target task data are left to intuition. We propose three cost-effective measures to quantify different aspects of similarity between source pretraining and target task data. We demonstrate that these measures are good predictors of the usefulness of pretrained models for Named Entity Recognition (NER) over 30 data pairs. Results also suggest that pretrained LMs "},"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":"1904.00585","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-01T06:45:45Z","cross_cats_sorted":[],"title_canon_sha256":"58ae46888147aa9e4a2ea559a78c2f55d8033b71bc4f87e9b8813da2196f5e0f","abstract_canon_sha256":"717107bf77f3e000008a2cdc085dc6bc1a174423d32936378c2d4cfae6c2e7e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:57.752748Z","signature_b64":"o88i9JtkTFAonJGVA8jVdL/vMKt2bWbx8yXlNH7yewi7bmRCDn9DeOqEZ1yIb44uI4/z4yiEdK0s+wXMNn4aAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"332fc8818549e26673714008f87e0c3e30c31527fecbc7f1e286b872889add9a","last_reissued_at":"2026-05-17T23:45:57.752223Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:57.752223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Similarity Measures to Select Pretraining Data for NER","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ben Hachey, Cecile Paris, Sarvnaz Karimi, Xiang Dai","submitted_at":"2019-04-01T06:45:45Z","abstract_excerpt":"Word vectors and Language Models (LMs) pretrained on a large amount of unlabelled data can dramatically improve various Natural Language Processing (NLP) tasks. However, the measure and impact of similarity between pretraining data and target task data are left to intuition. We propose three cost-effective measures to quantify different aspects of similarity between source pretraining and target task data. We demonstrate that these measures are good predictors of the usefulness of pretrained models for Named Entity Recognition (NER) over 30 data pairs. Results also suggest that pretrained LMs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.00585","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":""},"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":"1904.00585","created_at":"2026-05-17T23:45:57.752283+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.00585v2","created_at":"2026-05-17T23:45:57.752283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.00585","created_at":"2026-05-17T23:45:57.752283+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMX4RAMFJHRG","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMX4RAMFJHRGM43R","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMX4RAMF","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/GMX4RAMFJHRGM43RIAEPQ7QMHY","json":"https://pith.science/pith/GMX4RAMFJHRGM43RIAEPQ7QMHY.json","graph_json":"https://pith.science/api/pith-number/GMX4RAMFJHRGM43RIAEPQ7QMHY/graph.json","events_json":"https://pith.science/api/pith-number/GMX4RAMFJHRGM43RIAEPQ7QMHY/events.json","paper":"https://pith.science/paper/GMX4RAMF"},"agent_actions":{"view_html":"https://pith.science/pith/GMX4RAMFJHRGM43RIAEPQ7QMHY","download_json":"https://pith.science/pith/GMX4RAMFJHRGM43RIAEPQ7QMHY.json","view_paper":"https://pith.science/paper/GMX4RAMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.00585&json=true","fetch_graph":"https://pith.science/api/pith-number/GMX4RAMFJHRGM43RIAEPQ7QMHY/graph.json","fetch_events":"https://pith.science/api/pith-number/GMX4RAMFJHRGM43RIAEPQ7QMHY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMX4RAMFJHRGM43RIAEPQ7QMHY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMX4RAMFJHRGM43RIAEPQ7QMHY/action/storage_attestation","attest_author":"https://pith.science/pith/GMX4RAMFJHRGM43RIAEPQ7QMHY/action/author_attestation","sign_citation":"https://pith.science/pith/GMX4RAMFJHRGM43RIAEPQ7QMHY/action/citation_signature","submit_replication":"https://pith.science/pith/GMX4RAMFJHRGM43RIAEPQ7QMHY/action/replication_record"}},"created_at":"2026-05-17T23:45:57.752283+00:00","updated_at":"2026-05-17T23:45:57.752283+00:00"}