{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:C552HDCB6AMCY2EAUBH7YXZ5W7","short_pith_number":"pith:C552HDCB","schema_version":"1.0","canonical_sha256":"177ba38c41f0182c6880a04ffc5f3db7eba08d9821c9f1abbc0581512b9c1eda","source":{"kind":"arxiv","id":"2109.12573","version":3},"attestation_state":"computed","paper":{"title":"XLM-K: Improving Cross-Lingual Language Model Pre-training with Multilingual Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nan Duan, Weizhu Chen, Xiaoze Jiang, Yaobo Liang","submitted_at":"2021-09-26T11:46:20Z","abstract_excerpt":"Cross-lingual pre-training has achieved great successes using monolingual and bilingual plain text corpora. However, most pre-trained models neglect multilingual knowledge, which is language agnostic but comprises abundant cross-lingual structure alignment. In this paper, we propose XLM-K, a cross-lingual language model incorporating multilingual knowledge in pre-training. XLM-K augments existing multilingual pre-training with two knowledge tasks, namely Masked Entity Prediction Task and Object Entailment Task. We evaluate XLM-K on MLQA, NER and XNLI. Experimental results clearly demonstrate s"},"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":"2109.12573","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-26T11:46:20Z","cross_cats_sorted":[],"title_canon_sha256":"0e2bd5a6971ca372c43c9ac2ebff2f1ee4cedbde2bc238094420364aeebe0737","abstract_canon_sha256":"31bde00b18eb6cc69dda8cbb028806c1ff87310ab85821d85b296afef0a3cf10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:17.172488Z","signature_b64":"3knj/Gx4vGqGKVx7wf4fqfpxhQvwEGBqKqMGkplQQZlPREo1VeRo9U1y3QoDqyWFwsXel3AoHZbwD+AvvpFMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"177ba38c41f0182c6880a04ffc5f3db7eba08d9821c9f1abbc0581512b9c1eda","last_reissued_at":"2026-07-05T04:17:17.171936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:17.171936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XLM-K: Improving Cross-Lingual Language Model Pre-training with Multilingual Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nan Duan, Weizhu Chen, Xiaoze Jiang, Yaobo Liang","submitted_at":"2021-09-26T11:46:20Z","abstract_excerpt":"Cross-lingual pre-training has achieved great successes using monolingual and bilingual plain text corpora. However, most pre-trained models neglect multilingual knowledge, which is language agnostic but comprises abundant cross-lingual structure alignment. In this paper, we propose XLM-K, a cross-lingual language model incorporating multilingual knowledge in pre-training. XLM-K augments existing multilingual pre-training with two knowledge tasks, namely Masked Entity Prediction Task and Object Entailment Task. We evaluate XLM-K on MLQA, NER and XNLI. Experimental results clearly demonstrate s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.12573","kind":"arxiv","version":3},"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/2109.12573/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":"2109.12573","created_at":"2026-07-05T04:17:17.172003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.12573v3","created_at":"2026-07-05T04:17:17.172003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.12573","created_at":"2026-07-05T04:17:17.172003+00:00"},{"alias_kind":"pith_short_12","alias_value":"C552HDCB6AMC","created_at":"2026-07-05T04:17:17.172003+00:00"},{"alias_kind":"pith_short_16","alias_value":"C552HDCB6AMCY2EA","created_at":"2026-07-05T04:17:17.172003+00:00"},{"alias_kind":"pith_short_8","alias_value":"C552HDCB","created_at":"2026-07-05T04:17:17.172003+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/C552HDCB6AMCY2EAUBH7YXZ5W7","json":"https://pith.science/pith/C552HDCB6AMCY2EAUBH7YXZ5W7.json","graph_json":"https://pith.science/api/pith-number/C552HDCB6AMCY2EAUBH7YXZ5W7/graph.json","events_json":"https://pith.science/api/pith-number/C552HDCB6AMCY2EAUBH7YXZ5W7/events.json","paper":"https://pith.science/paper/C552HDCB"},"agent_actions":{"view_html":"https://pith.science/pith/C552HDCB6AMCY2EAUBH7YXZ5W7","download_json":"https://pith.science/pith/C552HDCB6AMCY2EAUBH7YXZ5W7.json","view_paper":"https://pith.science/paper/C552HDCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.12573&json=true","fetch_graph":"https://pith.science/api/pith-number/C552HDCB6AMCY2EAUBH7YXZ5W7/graph.json","fetch_events":"https://pith.science/api/pith-number/C552HDCB6AMCY2EAUBH7YXZ5W7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C552HDCB6AMCY2EAUBH7YXZ5W7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C552HDCB6AMCY2EAUBH7YXZ5W7/action/storage_attestation","attest_author":"https://pith.science/pith/C552HDCB6AMCY2EAUBH7YXZ5W7/action/author_attestation","sign_citation":"https://pith.science/pith/C552HDCB6AMCY2EAUBH7YXZ5W7/action/citation_signature","submit_replication":"https://pith.science/pith/C552HDCB6AMCY2EAUBH7YXZ5W7/action/replication_record"}},"created_at":"2026-07-05T04:17:17.172003+00:00","updated_at":"2026-07-05T04:17:17.172003+00:00"}