{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AELHHQ62YWY23KV6IHE5XKLEJB","short_pith_number":"pith:AELHHQ62","schema_version":"1.0","canonical_sha256":"011673c3dac5b1adaabe41c9dba96448527d20aaaf5b450e3c4d085b2efe36cb","source":{"kind":"arxiv","id":"2009.11538","version":3},"attestation_state":"computed","paper":{"title":"Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Ye, Hwee Tou Ng, Juntao Li, Lidong Bing, Qingyu Tan, Ruidan He","submitted_at":"2020-09-24T08:04:37Z","abstract_excerpt":"Adapting pre-trained language models (PrLMs) (e.g., BERT) to new domains has gained much attention recently. Instead of fine-tuning PrLMs as done in most previous work, we investigate how to adapt the features of PrLMs to new domains without fine-tuning. We explore unsupervised domain adaptation (UDA) in this paper. With the features from PrLMs, we adapt the models trained with labeled data from the source domain to the unlabeled target domain. Self-training is widely used for UDA which predicts pseudo labels on the target domain data for training. However, the predicted pseudo labels inevitab"},"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":"2009.11538","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-24T08:04:37Z","cross_cats_sorted":[],"title_canon_sha256":"9db9ea0512889163eee87ab7acc44a0f779f5139861f4cc394cb8a4141326b16","abstract_canon_sha256":"9fe51a5d909bcc69987c4452cc4e2913ac88ad0c09e8a06cfe3d72b552d4973f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:55:13.245113Z","signature_b64":"WRHkg7VLabPyzTJ08r8crye3P9l3iAk8ZVU0EwETj0rrWmaigrmmLMKKY66lNoKv1VnlUfu8gMfhrHd0oz7HBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"011673c3dac5b1adaabe41c9dba96448527d20aaaf5b450e3c4d085b2efe36cb","last_reissued_at":"2026-07-05T01:55:13.244641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:55:13.244641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Ye, Hwee Tou Ng, Juntao Li, Lidong Bing, Qingyu Tan, Ruidan He","submitted_at":"2020-09-24T08:04:37Z","abstract_excerpt":"Adapting pre-trained language models (PrLMs) (e.g., BERT) to new domains has gained much attention recently. Instead of fine-tuning PrLMs as done in most previous work, we investigate how to adapt the features of PrLMs to new domains without fine-tuning. We explore unsupervised domain adaptation (UDA) in this paper. With the features from PrLMs, we adapt the models trained with labeled data from the source domain to the unlabeled target domain. Self-training is widely used for UDA which predicts pseudo labels on the target domain data for training. However, the predicted pseudo labels inevitab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.11538","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/2009.11538/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":"2009.11538","created_at":"2026-07-05T01:55:13.244698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.11538v3","created_at":"2026-07-05T01:55:13.244698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.11538","created_at":"2026-07-05T01:55:13.244698+00:00"},{"alias_kind":"pith_short_12","alias_value":"AELHHQ62YWY2","created_at":"2026-07-05T01:55:13.244698+00:00"},{"alias_kind":"pith_short_16","alias_value":"AELHHQ62YWY23KV6","created_at":"2026-07-05T01:55:13.244698+00:00"},{"alias_kind":"pith_short_8","alias_value":"AELHHQ62","created_at":"2026-07-05T01:55:13.244698+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/AELHHQ62YWY23KV6IHE5XKLEJB","json":"https://pith.science/pith/AELHHQ62YWY23KV6IHE5XKLEJB.json","graph_json":"https://pith.science/api/pith-number/AELHHQ62YWY23KV6IHE5XKLEJB/graph.json","events_json":"https://pith.science/api/pith-number/AELHHQ62YWY23KV6IHE5XKLEJB/events.json","paper":"https://pith.science/paper/AELHHQ62"},"agent_actions":{"view_html":"https://pith.science/pith/AELHHQ62YWY23KV6IHE5XKLEJB","download_json":"https://pith.science/pith/AELHHQ62YWY23KV6IHE5XKLEJB.json","view_paper":"https://pith.science/paper/AELHHQ62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.11538&json=true","fetch_graph":"https://pith.science/api/pith-number/AELHHQ62YWY23KV6IHE5XKLEJB/graph.json","fetch_events":"https://pith.science/api/pith-number/AELHHQ62YWY23KV6IHE5XKLEJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AELHHQ62YWY23KV6IHE5XKLEJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AELHHQ62YWY23KV6IHE5XKLEJB/action/storage_attestation","attest_author":"https://pith.science/pith/AELHHQ62YWY23KV6IHE5XKLEJB/action/author_attestation","sign_citation":"https://pith.science/pith/AELHHQ62YWY23KV6IHE5XKLEJB/action/citation_signature","submit_replication":"https://pith.science/pith/AELHHQ62YWY23KV6IHE5XKLEJB/action/replication_record"}},"created_at":"2026-07-05T01:55:13.244698+00:00","updated_at":"2026-07-05T01:55:13.244698+00:00"}