{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JF4GQT4QH2DH6OAVI5CJNUIVVS","short_pith_number":"pith:JF4GQT4Q","schema_version":"1.0","canonical_sha256":"4978684f903e867f3815474496d115ac8d041fb0df7e4a2420a968fc730df67c","source":{"kind":"arxiv","id":"1906.05039","version":1},"attestation_state":"computed","paper":{"title":"Concept Discovery through Information Extraction in Restaurant Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charith Chitraranjan, Nadeesha Pathirana, Rangika Samarawickrama, Sandaru Seneviratne, Shane Wolff, Tharindu Ranasinghe, Uthayasanker Thayasivam","submitted_at":"2019-06-12T09:55:20Z","abstract_excerpt":"Concept identification is a crucial step in understanding and building a knowledge base for any particular domain. However, it is not a simple task in very large domains such as restaurants and hotel. In this paper, a novel approach of identifying a concept hierarchy and classifying unseen words into identified concepts related to restaurant domain is presented. Sorting, identifying, classifying of domain-related words manually is tedious and therefore, the proposed process is automated to a great extent. Word embedding, hierarchical clustering, classification algorithms are effectively used t"},"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":"1906.05039","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-12T09:55:20Z","cross_cats_sorted":[],"title_canon_sha256":"27b48a47a8260121f0302d5de3afa8e3430961f3e0d0ff65a2765ef5a3c59247","abstract_canon_sha256":"89631d93ffff24d7cdc3033bc28561e9ff1437441388dcd083c907909ed800be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:29.664290Z","signature_b64":"qQ+mpS5ytLHkztGZYOBIQwEweKMl7dIoST6su99cePJjL55EwMTyIr5+vR9oEitWo3JN1WDdSLPlK/xZFn7PCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4978684f903e867f3815474496d115ac8d041fb0df7e4a2420a968fc730df67c","last_reissued_at":"2026-05-17T23:43:29.663547Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:29.663547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Concept Discovery through Information Extraction in Restaurant Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charith Chitraranjan, Nadeesha Pathirana, Rangika Samarawickrama, Sandaru Seneviratne, Shane Wolff, Tharindu Ranasinghe, Uthayasanker Thayasivam","submitted_at":"2019-06-12T09:55:20Z","abstract_excerpt":"Concept identification is a crucial step in understanding and building a knowledge base for any particular domain. However, it is not a simple task in very large domains such as restaurants and hotel. In this paper, a novel approach of identifying a concept hierarchy and classifying unseen words into identified concepts related to restaurant domain is presented. Sorting, identifying, classifying of domain-related words manually is tedious and therefore, the proposed process is automated to a great extent. Word embedding, hierarchical clustering, classification algorithms are effectively used t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05039","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":"1906.05039","created_at":"2026-05-17T23:43:29.663681+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05039v1","created_at":"2026-05-17T23:43:29.663681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05039","created_at":"2026-05-17T23:43:29.663681+00:00"},{"alias_kind":"pith_short_12","alias_value":"JF4GQT4QH2DH","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"JF4GQT4QH2DH6OAV","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"JF4GQT4Q","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/JF4GQT4QH2DH6OAVI5CJNUIVVS","json":"https://pith.science/pith/JF4GQT4QH2DH6OAVI5CJNUIVVS.json","graph_json":"https://pith.science/api/pith-number/JF4GQT4QH2DH6OAVI5CJNUIVVS/graph.json","events_json":"https://pith.science/api/pith-number/JF4GQT4QH2DH6OAVI5CJNUIVVS/events.json","paper":"https://pith.science/paper/JF4GQT4Q"},"agent_actions":{"view_html":"https://pith.science/pith/JF4GQT4QH2DH6OAVI5CJNUIVVS","download_json":"https://pith.science/pith/JF4GQT4QH2DH6OAVI5CJNUIVVS.json","view_paper":"https://pith.science/paper/JF4GQT4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05039&json=true","fetch_graph":"https://pith.science/api/pith-number/JF4GQT4QH2DH6OAVI5CJNUIVVS/graph.json","fetch_events":"https://pith.science/api/pith-number/JF4GQT4QH2DH6OAVI5CJNUIVVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JF4GQT4QH2DH6OAVI5CJNUIVVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JF4GQT4QH2DH6OAVI5CJNUIVVS/action/storage_attestation","attest_author":"https://pith.science/pith/JF4GQT4QH2DH6OAVI5CJNUIVVS/action/author_attestation","sign_citation":"https://pith.science/pith/JF4GQT4QH2DH6OAVI5CJNUIVVS/action/citation_signature","submit_replication":"https://pith.science/pith/JF4GQT4QH2DH6OAVI5CJNUIVVS/action/replication_record"}},"created_at":"2026-05-17T23:43:29.663681+00:00","updated_at":"2026-05-17T23:43:29.663681+00:00"}