{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BPJHJU3H4VGCANQLSJECYPUFM6","short_pith_number":"pith:BPJHJU3H","schema_version":"1.0","canonical_sha256":"0bd274d367e54c20360b92482c3e8567b46ef7cd8595cdc676366088e36338c8","source":{"kind":"arxiv","id":"2110.07792","version":2},"attestation_state":"computed","paper":{"title":"A Multilingual Bag-of-Entities Model for Zero-Shot Cross-Lingual Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ikuya Yamada, Isao Echizen, Sosuke Nishikawa, Yoshimasa Tsuruoka","submitted_at":"2021-10-15T01:10:50Z","abstract_excerpt":"We present a multilingual bag-of-entities model that effectively boosts the performance of zero-shot cross-lingual text classification by extending a multilingual pre-trained language model (e.g., M-BERT). It leverages the multilingual nature of Wikidata: entities in multiple languages representing the same concept are defined with a unique identifier. This enables entities described in multiple languages to be represented using shared embeddings. A model trained on entity features in a resource-rich language can thus be directly applied to other languages. Our experimental results on cross-li"},"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":"2110.07792","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T01:10:50Z","cross_cats_sorted":[],"title_canon_sha256":"a95990b44c5d1c198f718c0392867570271aa7170be171a90bc261cd93d3da01","abstract_canon_sha256":"f2ec48b39e3d9d4dc280f90f2c4c291abc6da270b5cc13b4e44b97c29aa88b5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:01.075775Z","signature_b64":"hDaykUbf9lHXftDm6+/trfp08Idm4q7Pd0kpyvRtvH4PkYfcqTM8l7xwnlfxLGcHH6DQrZpZv967XoLb6eK5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bd274d367e54c20360b92482c3e8567b46ef7cd8595cdc676366088e36338c8","last_reissued_at":"2026-07-05T05:05:01.075365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:01.075365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multilingual Bag-of-Entities Model for Zero-Shot Cross-Lingual Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ikuya Yamada, Isao Echizen, Sosuke Nishikawa, Yoshimasa Tsuruoka","submitted_at":"2021-10-15T01:10:50Z","abstract_excerpt":"We present a multilingual bag-of-entities model that effectively boosts the performance of zero-shot cross-lingual text classification by extending a multilingual pre-trained language model (e.g., M-BERT). It leverages the multilingual nature of Wikidata: entities in multiple languages representing the same concept are defined with a unique identifier. This enables entities described in multiple languages to be represented using shared embeddings. A model trained on entity features in a resource-rich language can thus be directly applied to other languages. Our experimental results on cross-li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07792","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/2110.07792/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":"2110.07792","created_at":"2026-07-05T05:05:01.075422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07792v2","created_at":"2026-07-05T05:05:01.075422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07792","created_at":"2026-07-05T05:05:01.075422+00:00"},{"alias_kind":"pith_short_12","alias_value":"BPJHJU3H4VGC","created_at":"2026-07-05T05:05:01.075422+00:00"},{"alias_kind":"pith_short_16","alias_value":"BPJHJU3H4VGCANQL","created_at":"2026-07-05T05:05:01.075422+00:00"},{"alias_kind":"pith_short_8","alias_value":"BPJHJU3H","created_at":"2026-07-05T05:05:01.075422+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/BPJHJU3H4VGCANQLSJECYPUFM6","json":"https://pith.science/pith/BPJHJU3H4VGCANQLSJECYPUFM6.json","graph_json":"https://pith.science/api/pith-number/BPJHJU3H4VGCANQLSJECYPUFM6/graph.json","events_json":"https://pith.science/api/pith-number/BPJHJU3H4VGCANQLSJECYPUFM6/events.json","paper":"https://pith.science/paper/BPJHJU3H"},"agent_actions":{"view_html":"https://pith.science/pith/BPJHJU3H4VGCANQLSJECYPUFM6","download_json":"https://pith.science/pith/BPJHJU3H4VGCANQLSJECYPUFM6.json","view_paper":"https://pith.science/paper/BPJHJU3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07792&json=true","fetch_graph":"https://pith.science/api/pith-number/BPJHJU3H4VGCANQLSJECYPUFM6/graph.json","fetch_events":"https://pith.science/api/pith-number/BPJHJU3H4VGCANQLSJECYPUFM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BPJHJU3H4VGCANQLSJECYPUFM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BPJHJU3H4VGCANQLSJECYPUFM6/action/storage_attestation","attest_author":"https://pith.science/pith/BPJHJU3H4VGCANQLSJECYPUFM6/action/author_attestation","sign_citation":"https://pith.science/pith/BPJHJU3H4VGCANQLSJECYPUFM6/action/citation_signature","submit_replication":"https://pith.science/pith/BPJHJU3H4VGCANQLSJECYPUFM6/action/replication_record"}},"created_at":"2026-07-05T05:05:01.075422+00:00","updated_at":"2026-07-05T05:05:01.075422+00:00"}