{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FWIPWPAMJMQETSRCZNTI7BOJ5M","short_pith_number":"pith:FWIPWPAM","schema_version":"1.0","canonical_sha256":"2d90fb3c0c4b2049ca22cb668f85c9eb265d000d6d1b639c4897fc6a308f300c","source":{"kind":"arxiv","id":"2104.03767","version":2},"attestation_state":"computed","paper":{"title":"Uppsala NLP at SemEval-2021 Task 2: Multilingual Language Models for Fine-tuning and Feature Extraction in Word-in-Context Disambiguation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huiling You, Sara Stymne, Xingran Zhu","submitted_at":"2021-04-08T13:40:41Z","abstract_excerpt":"We describe the Uppsala NLP submission to SemEval-2021 Task 2 on multilingual and cross-lingual word-in-context disambiguation. We explore the usefulness of three pre-trained multilingual language models, XLM-RoBERTa (XLMR), Multilingual BERT (mBERT) and multilingual distilled BERT (mDistilBERT). We compare these three models in two setups, fine-tuning and as feature extractors. In the second case we also experiment with using dependency-based information. We find that fine-tuning is better than feature extraction. XLMR performs better than mBERT in the cross-lingual setting both with fine-tun"},"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":"2104.03767","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-08T13:40:41Z","cross_cats_sorted":[],"title_canon_sha256":"e5806f5ab44e5e0bcc713ace3cb94cc252acd98a6338763f7d29a70bb768aac4","abstract_canon_sha256":"b7d63239c54a5c319a806cfcbd467d46f3f526ff58b7777f199e3c19876ff0da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:33.217287Z","signature_b64":"Ce/i8YMCWpxRHq2vHYZ0Q8d5NadGVlXHvCWM2xaeu8FeFH2N1IdP0Ga/h/KjshTihDj9IRDFaOhXQRGoZSckBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d90fb3c0c4b2049ca22cb668f85c9eb265d000d6d1b639c4897fc6a308f300c","last_reissued_at":"2026-07-05T02:30:33.216830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:33.216830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uppsala NLP at SemEval-2021 Task 2: Multilingual Language Models for Fine-tuning and Feature Extraction in Word-in-Context Disambiguation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huiling You, Sara Stymne, Xingran Zhu","submitted_at":"2021-04-08T13:40:41Z","abstract_excerpt":"We describe the Uppsala NLP submission to SemEval-2021 Task 2 on multilingual and cross-lingual word-in-context disambiguation. We explore the usefulness of three pre-trained multilingual language models, XLM-RoBERTa (XLMR), Multilingual BERT (mBERT) and multilingual distilled BERT (mDistilBERT). We compare these three models in two setups, fine-tuning and as feature extractors. In the second case we also experiment with using dependency-based information. We find that fine-tuning is better than feature extraction. XLMR performs better than mBERT in the cross-lingual setting both with fine-tun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03767","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/2104.03767/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":"2104.03767","created_at":"2026-07-05T02:30:33.216886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.03767v2","created_at":"2026-07-05T02:30:33.216886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03767","created_at":"2026-07-05T02:30:33.216886+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWIPWPAMJMQE","created_at":"2026-07-05T02:30:33.216886+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWIPWPAMJMQETSRC","created_at":"2026-07-05T02:30:33.216886+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWIPWPAM","created_at":"2026-07-05T02:30:33.216886+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02391","citing_title":"FewTopNER: Integrating Few-Shot Learning with Topic Modeling and Named Entity Recognition in a Multilingual Framework","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M","json":"https://pith.science/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M.json","graph_json":"https://pith.science/api/pith-number/FWIPWPAMJMQETSRCZNTI7BOJ5M/graph.json","events_json":"https://pith.science/api/pith-number/FWIPWPAMJMQETSRCZNTI7BOJ5M/events.json","paper":"https://pith.science/paper/FWIPWPAM"},"agent_actions":{"view_html":"https://pith.science/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M","download_json":"https://pith.science/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M.json","view_paper":"https://pith.science/paper/FWIPWPAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.03767&json=true","fetch_graph":"https://pith.science/api/pith-number/FWIPWPAMJMQETSRCZNTI7BOJ5M/graph.json","fetch_events":"https://pith.science/api/pith-number/FWIPWPAMJMQETSRCZNTI7BOJ5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M/action/storage_attestation","attest_author":"https://pith.science/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M/action/author_attestation","sign_citation":"https://pith.science/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M/action/citation_signature","submit_replication":"https://pith.science/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M/action/replication_record"}},"created_at":"2026-07-05T02:30:33.216886+00:00","updated_at":"2026-07-05T02:30:33.216886+00:00"}