{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CSVXA27U6SDWBKOEOEE2VDX7GV","short_pith_number":"pith:CSVXA27U","schema_version":"1.0","canonical_sha256":"14ab706bf4f48760a9c47109aa8eff3545e14f5ef5fe53e41da4cf74725220cb","source":{"kind":"arxiv","id":"2009.03706","version":1},"attestation_state":"computed","paper":{"title":"ERNIE at SemEval-2020 Task 10: Learning Word Emphasis Selection by Pre-trained Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiaxiang Liu, Shikun Feng, Shuohuan Wang, Weiyue Su, Xuan Ouyang, Xuyi Chen, Yu Sun, Zhengjie Huang","submitted_at":"2020-09-08T12:51:22Z","abstract_excerpt":"This paper describes the system designed by ERNIE Team which achieved the first place in SemEval-2020 Task 10: Emphasis Selection For Written Text in Visual Media. Given a sentence, we are asked to find out the most important words as the suggestion for automated design. We leverage the unsupervised pre-training model and finetune these models on our task. After our investigation, we found that the following models achieved an excellent performance in this task: ERNIE 2.0, XLM-ROBERTA, ROBERTA and ALBERT. We combine a pointwise regression loss and a pairwise ranking loss which is more close to"},"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":"2009.03706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-08T12:51:22Z","cross_cats_sorted":[],"title_canon_sha256":"bcca202bc31af602e08e5e99585097e56634c9b14e71ea45d052cdbdf3501d2a","abstract_canon_sha256":"bda7740abe0f1a1d9a31d1f494899bd86f3913c253aa1c042f1d231f63e8280c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:33:50.112430Z","signature_b64":"GgqdPiscHtfDlNyIRA9DT+g+F0Hc80j8JkkCyPx0lbc6uiciIBo/6huCg3dB4kVdvSYrZ207Zrw5oRneeuC/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14ab706bf4f48760a9c47109aa8eff3545e14f5ef5fe53e41da4cf74725220cb","last_reissued_at":"2026-07-05T01:33:50.112076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:33:50.112076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ERNIE at SemEval-2020 Task 10: Learning Word Emphasis Selection by Pre-trained Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiaxiang Liu, Shikun Feng, Shuohuan Wang, Weiyue Su, Xuan Ouyang, Xuyi Chen, Yu Sun, Zhengjie Huang","submitted_at":"2020-09-08T12:51:22Z","abstract_excerpt":"This paper describes the system designed by ERNIE Team which achieved the first place in SemEval-2020 Task 10: Emphasis Selection For Written Text in Visual Media. Given a sentence, we are asked to find out the most important words as the suggestion for automated design. We leverage the unsupervised pre-training model and finetune these models on our task. After our investigation, we found that the following models achieved an excellent performance in this task: ERNIE 2.0, XLM-ROBERTA, ROBERTA and ALBERT. We combine a pointwise regression loss and a pairwise ranking loss which is more close to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.03706","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/2009.03706/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":"2009.03706","created_at":"2026-07-05T01:33:50.112138+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.03706v1","created_at":"2026-07-05T01:33:50.112138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.03706","created_at":"2026-07-05T01:33:50.112138+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSVXA27U6SDW","created_at":"2026-07-05T01:33:50.112138+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSVXA27U6SDWBKOE","created_at":"2026-07-05T01:33:50.112138+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSVXA27U","created_at":"2026-07-05T01:33:50.112138+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/CSVXA27U6SDWBKOEOEE2VDX7GV","json":"https://pith.science/pith/CSVXA27U6SDWBKOEOEE2VDX7GV.json","graph_json":"https://pith.science/api/pith-number/CSVXA27U6SDWBKOEOEE2VDX7GV/graph.json","events_json":"https://pith.science/api/pith-number/CSVXA27U6SDWBKOEOEE2VDX7GV/events.json","paper":"https://pith.science/paper/CSVXA27U"},"agent_actions":{"view_html":"https://pith.science/pith/CSVXA27U6SDWBKOEOEE2VDX7GV","download_json":"https://pith.science/pith/CSVXA27U6SDWBKOEOEE2VDX7GV.json","view_paper":"https://pith.science/paper/CSVXA27U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.03706&json=true","fetch_graph":"https://pith.science/api/pith-number/CSVXA27U6SDWBKOEOEE2VDX7GV/graph.json","fetch_events":"https://pith.science/api/pith-number/CSVXA27U6SDWBKOEOEE2VDX7GV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSVXA27U6SDWBKOEOEE2VDX7GV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSVXA27U6SDWBKOEOEE2VDX7GV/action/storage_attestation","attest_author":"https://pith.science/pith/CSVXA27U6SDWBKOEOEE2VDX7GV/action/author_attestation","sign_citation":"https://pith.science/pith/CSVXA27U6SDWBKOEOEE2VDX7GV/action/citation_signature","submit_replication":"https://pith.science/pith/CSVXA27U6SDWBKOEOEE2VDX7GV/action/replication_record"}},"created_at":"2026-07-05T01:33:50.112138+00:00","updated_at":"2026-07-05T01:33:50.112138+00:00"}