{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XE3R4EYLAMX7OKEFQBJDX2NXVO","short_pith_number":"pith:XE3R4EYL","schema_version":"1.0","canonical_sha256":"b9371e130b032ff7288580523be9b7abb6df4bb837a5b60b04e8db4738db0985","source":{"kind":"arxiv","id":"2101.11112","version":1},"attestation_state":"computed","paper":{"title":"Cross-Lingual Named Entity Recognition Using Parallel Corpus: A New Approach Using XLM-RoBERTa Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Li, Wenjin Xu, Yujie He","submitted_at":"2021-01-26T22:19:52Z","abstract_excerpt":"We propose a novel approach for cross-lingual Named Entity Recognition (NER) zero-shot transfer using parallel corpora. We built an entity alignment model on top of XLM-RoBERTa to project the entities detected on the English part of the parallel data to the target language sentences, whose accuracy surpasses all previous unsupervised models. With the alignment model we can get pseudo-labeled NER data set in the target language to train task-specific model. Unlike using translation methods, this approach benefits from natural fluency and nuances in target-language original corpus. We also propo"},"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":"2101.11112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-26T22:19:52Z","cross_cats_sorted":[],"title_canon_sha256":"42543946b241c6048abf08b69463ef3d259ca0978053a85ae43290977f322ca0","abstract_canon_sha256":"b5330827d7ab09471394a4a7cbad97c2d20c3cc1f3cc349691f3a9631a85c0c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:09.141472Z","signature_b64":"Nx16Xgv20cuQX/pjRQStv50l5AHvJMV3LgZjyNIGDauR1hawnJOZO+waYns2UVWXmq/K3bvcAErPr4aApBgWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9371e130b032ff7288580523be9b7abb6df4bb837a5b60b04e8db4738db0985","last_reissued_at":"2026-07-05T02:10:09.141005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:09.141005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Lingual Named Entity Recognition Using Parallel Corpus: A New Approach Using XLM-RoBERTa Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Li, Wenjin Xu, Yujie He","submitted_at":"2021-01-26T22:19:52Z","abstract_excerpt":"We propose a novel approach for cross-lingual Named Entity Recognition (NER) zero-shot transfer using parallel corpora. We built an entity alignment model on top of XLM-RoBERTa to project the entities detected on the English part of the parallel data to the target language sentences, whose accuracy surpasses all previous unsupervised models. With the alignment model we can get pseudo-labeled NER data set in the target language to train task-specific model. Unlike using translation methods, this approach benefits from natural fluency and nuances in target-language original corpus. We also propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11112","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2101.11112/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":"2101.11112","created_at":"2026-07-05T02:10:09.141083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.11112v1","created_at":"2026-07-05T02:10:09.141083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11112","created_at":"2026-07-05T02:10:09.141083+00:00"},{"alias_kind":"pith_short_12","alias_value":"XE3R4EYLAMX7","created_at":"2026-07-05T02:10:09.141083+00:00"},{"alias_kind":"pith_short_16","alias_value":"XE3R4EYLAMX7OKEF","created_at":"2026-07-05T02:10:09.141083+00:00"},{"alias_kind":"pith_short_8","alias_value":"XE3R4EYL","created_at":"2026-07-05T02:10:09.141083+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02722","citing_title":"Cross-Lingual Transfer for Low-Resource Natural Language Processing","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XE3R4EYLAMX7OKEFQBJDX2NXVO","json":"https://pith.science/pith/XE3R4EYLAMX7OKEFQBJDX2NXVO.json","graph_json":"https://pith.science/api/pith-number/XE3R4EYLAMX7OKEFQBJDX2NXVO/graph.json","events_json":"https://pith.science/api/pith-number/XE3R4EYLAMX7OKEFQBJDX2NXVO/events.json","paper":"https://pith.science/paper/XE3R4EYL"},"agent_actions":{"view_html":"https://pith.science/pith/XE3R4EYLAMX7OKEFQBJDX2NXVO","download_json":"https://pith.science/pith/XE3R4EYLAMX7OKEFQBJDX2NXVO.json","view_paper":"https://pith.science/paper/XE3R4EYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.11112&json=true","fetch_graph":"https://pith.science/api/pith-number/XE3R4EYLAMX7OKEFQBJDX2NXVO/graph.json","fetch_events":"https://pith.science/api/pith-number/XE3R4EYLAMX7OKEFQBJDX2NXVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XE3R4EYLAMX7OKEFQBJDX2NXVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XE3R4EYLAMX7OKEFQBJDX2NXVO/action/storage_attestation","attest_author":"https://pith.science/pith/XE3R4EYLAMX7OKEFQBJDX2NXVO/action/author_attestation","sign_citation":"https://pith.science/pith/XE3R4EYLAMX7OKEFQBJDX2NXVO/action/citation_signature","submit_replication":"https://pith.science/pith/XE3R4EYLAMX7OKEFQBJDX2NXVO/action/replication_record"}},"created_at":"2026-07-05T02:10:09.141083+00:00","updated_at":"2026-07-05T02:10:09.141083+00:00"}