{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WF2GP6XMQS2NAVFTRDM3WRCB4O","short_pith_number":"pith:WF2GP6XM","schema_version":"1.0","canonical_sha256":"b17467faec84b4d054b388d9bb4441e3b4232cf8464d3b7003dc68a97a4fa18f","source":{"kind":"arxiv","id":"1911.04669","version":2},"attestation_state":"computed","paper":{"title":"How to Evaluate Word Representations of Informal Domain?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Lopez, Naomi Saphra, Yekun Chai","submitted_at":"2019-11-12T04:38:19Z","abstract_excerpt":"Diverse word representations have surged in most state-of-the-art natural language processing (NLP) applications. Nevertheless, how to efficiently evaluate such word embeddings in the informal domain such as Twitter or forums, remains an ongoing challenge due to the lack of sufficient evaluation dataset. We derived a large list of variant spelling pairs from UrbanDictionary with the automatic approaches of weakly-supervised pattern-based bootstrapping and self-training linear-chain conditional random field (CRF). With these extracted relation pairs we promote the odds of eliding the text norma"},"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":"1911.04669","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-12T04:38:19Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"050c7b8c9194c564569cf4886013a119808a47c2674601084799e796c961b7bd","abstract_canon_sha256":"99a8bc8987297fe8655b899e94cd65ae8642e1428d2b6ea6168212c8e491847a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:18:53.627373Z","signature_b64":"CgmOH64OADv5QwdVZiagDPback5pGPzqVjMUKY+pTbMH/2LJ46ckn5iJvAXZs5RAQaLFeIUxGNc/yXpPwmo4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b17467faec84b4d054b388d9bb4441e3b4232cf8464d3b7003dc68a97a4fa18f","last_reissued_at":"2026-07-05T00:18:53.626962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:18:53.626962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Evaluate Word Representations of Informal Domain?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Lopez, Naomi Saphra, Yekun Chai","submitted_at":"2019-11-12T04:38:19Z","abstract_excerpt":"Diverse word representations have surged in most state-of-the-art natural language processing (NLP) applications. Nevertheless, how to efficiently evaluate such word embeddings in the informal domain such as Twitter or forums, remains an ongoing challenge due to the lack of sufficient evaluation dataset. We derived a large list of variant spelling pairs from UrbanDictionary with the automatic approaches of weakly-supervised pattern-based bootstrapping and self-training linear-chain conditional random field (CRF). With these extracted relation pairs we promote the odds of eliding the text norma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.04669","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/1911.04669/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":"1911.04669","created_at":"2026-07-05T00:18:53.627019+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.04669v2","created_at":"2026-07-05T00:18:53.627019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.04669","created_at":"2026-07-05T00:18:53.627019+00:00"},{"alias_kind":"pith_short_12","alias_value":"WF2GP6XMQS2N","created_at":"2026-07-05T00:18:53.627019+00:00"},{"alias_kind":"pith_short_16","alias_value":"WF2GP6XMQS2NAVFT","created_at":"2026-07-05T00:18:53.627019+00:00"},{"alias_kind":"pith_short_8","alias_value":"WF2GP6XM","created_at":"2026-07-05T00:18:53.627019+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/WF2GP6XMQS2NAVFTRDM3WRCB4O","json":"https://pith.science/pith/WF2GP6XMQS2NAVFTRDM3WRCB4O.json","graph_json":"https://pith.science/api/pith-number/WF2GP6XMQS2NAVFTRDM3WRCB4O/graph.json","events_json":"https://pith.science/api/pith-number/WF2GP6XMQS2NAVFTRDM3WRCB4O/events.json","paper":"https://pith.science/paper/WF2GP6XM"},"agent_actions":{"view_html":"https://pith.science/pith/WF2GP6XMQS2NAVFTRDM3WRCB4O","download_json":"https://pith.science/pith/WF2GP6XMQS2NAVFTRDM3WRCB4O.json","view_paper":"https://pith.science/paper/WF2GP6XM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.04669&json=true","fetch_graph":"https://pith.science/api/pith-number/WF2GP6XMQS2NAVFTRDM3WRCB4O/graph.json","fetch_events":"https://pith.science/api/pith-number/WF2GP6XMQS2NAVFTRDM3WRCB4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WF2GP6XMQS2NAVFTRDM3WRCB4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WF2GP6XMQS2NAVFTRDM3WRCB4O/action/storage_attestation","attest_author":"https://pith.science/pith/WF2GP6XMQS2NAVFTRDM3WRCB4O/action/author_attestation","sign_citation":"https://pith.science/pith/WF2GP6XMQS2NAVFTRDM3WRCB4O/action/citation_signature","submit_replication":"https://pith.science/pith/WF2GP6XMQS2NAVFTRDM3WRCB4O/action/replication_record"}},"created_at":"2026-07-05T00:18:53.627019+00:00","updated_at":"2026-07-05T00:18:53.627019+00:00"}