{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AQDFSMP5ZNVCMWP4OGMYC2LDZ4","short_pith_number":"pith:AQDFSMP5","schema_version":"1.0","canonical_sha256":"04065931fdcb6a2659fc7199816963cf3b78ed6c838a96384e15612d05da727e","source":{"kind":"arxiv","id":"2103.06418","version":1},"attestation_state":"computed","paper":{"title":"LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fang Wang, Lifeng Shang, Linlin Li, Qun Liu, Xiao Chen, Xiaoqi Jiao, Xin Jiang, Yichun Yin","submitted_at":"2021-03-11T02:24:41Z","abstract_excerpt":"The multilingual pre-trained language models (e.g, mBERT, XLM and XLM-R) have shown impressive performance on cross-lingual natural language understanding tasks. However, these models are computationally intensive and difficult to be deployed on resource-restricted devices. In this paper, we propose a simple yet effective distillation method (LightMBERT) for transferring the cross-lingual generalization ability of the multilingual BERT to a small student model. The experiment results empirically demonstrate the efficiency and effectiveness of LightMBERT, which is significantly better than the "},"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":"2103.06418","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-11T02:24:41Z","cross_cats_sorted":[],"title_canon_sha256":"254a83816a5053e4ef1d36a1d47884cc7d8a1cbade6239e5a64b867ba39ceddf","abstract_canon_sha256":"b63483095545c9694b5124f24233ffa4686c65dc5a39d9a30e04597cd28201e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:08.901232Z","signature_b64":"gFzRL3ftEtHZB0NZAKktcdwWX05z9omjqPtCn/1GNIXIspZj6uoUGv2efFmzYQ8sAHrnquLMzHklGHgdnRbwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04065931fdcb6a2659fc7199816963cf3b78ed6c838a96384e15612d05da727e","last_reissued_at":"2026-07-05T02:22:08.900793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:08.900793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fang Wang, Lifeng Shang, Linlin Li, Qun Liu, Xiao Chen, Xiaoqi Jiao, Xin Jiang, Yichun Yin","submitted_at":"2021-03-11T02:24:41Z","abstract_excerpt":"The multilingual pre-trained language models (e.g, mBERT, XLM and XLM-R) have shown impressive performance on cross-lingual natural language understanding tasks. However, these models are computationally intensive and difficult to be deployed on resource-restricted devices. In this paper, we propose a simple yet effective distillation method (LightMBERT) for transferring the cross-lingual generalization ability of the multilingual BERT to a small student model. The experiment results empirically demonstrate the efficiency and effectiveness of LightMBERT, which is significantly better than the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06418","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/2103.06418/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":"2103.06418","created_at":"2026-07-05T02:22:08.900855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.06418v1","created_at":"2026-07-05T02:22:08.900855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06418","created_at":"2026-07-05T02:22:08.900855+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQDFSMP5ZNVC","created_at":"2026-07-05T02:22:08.900855+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQDFSMP5ZNVCMWP4","created_at":"2026-07-05T02:22:08.900855+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQDFSMP5","created_at":"2026-07-05T02:22:08.900855+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/AQDFSMP5ZNVCMWP4OGMYC2LDZ4","json":"https://pith.science/pith/AQDFSMP5ZNVCMWP4OGMYC2LDZ4.json","graph_json":"https://pith.science/api/pith-number/AQDFSMP5ZNVCMWP4OGMYC2LDZ4/graph.json","events_json":"https://pith.science/api/pith-number/AQDFSMP5ZNVCMWP4OGMYC2LDZ4/events.json","paper":"https://pith.science/paper/AQDFSMP5"},"agent_actions":{"view_html":"https://pith.science/pith/AQDFSMP5ZNVCMWP4OGMYC2LDZ4","download_json":"https://pith.science/pith/AQDFSMP5ZNVCMWP4OGMYC2LDZ4.json","view_paper":"https://pith.science/paper/AQDFSMP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.06418&json=true","fetch_graph":"https://pith.science/api/pith-number/AQDFSMP5ZNVCMWP4OGMYC2LDZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/AQDFSMP5ZNVCMWP4OGMYC2LDZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQDFSMP5ZNVCMWP4OGMYC2LDZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQDFSMP5ZNVCMWP4OGMYC2LDZ4/action/storage_attestation","attest_author":"https://pith.science/pith/AQDFSMP5ZNVCMWP4OGMYC2LDZ4/action/author_attestation","sign_citation":"https://pith.science/pith/AQDFSMP5ZNVCMWP4OGMYC2LDZ4/action/citation_signature","submit_replication":"https://pith.science/pith/AQDFSMP5ZNVCMWP4OGMYC2LDZ4/action/replication_record"}},"created_at":"2026-07-05T02:22:08.900855+00:00","updated_at":"2026-07-05T02:22:08.900855+00:00"}