{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:G4JTCSFY2UJJIIWN7I36DWAOB5","short_pith_number":"pith:G4JTCSFY","schema_version":"1.0","canonical_sha256":"37133148b8d5129422cdfa37e1d80e0f6577ad80e4ebb6246b6d2217abd72d19","source":{"kind":"arxiv","id":"2112.08547","version":2},"attestation_state":"computed","paper":{"title":"Learning Rich Representation of Keyphrases from Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Debanjan Mahata, Mayank Kulkarni, Rajarshi Bhowmik, Ravneet Arora","submitted_at":"2021-12-16T01:09:51Z","abstract_excerpt":"In this work, we explore how to train task-specific language models aimed towards learning rich representation of keyphrases from text documents. We experiment with different masking strategies for pre-training transformer language models (LMs) in discriminative as well as generative settings. In the discriminative setting, we introduce a new pre-training objective - Keyphrase Boundary Infilling with Replacement (KBIR), showing large gains in performance (upto 8.16 points in F1) over SOTA, when the LM pre-trained using KBIR is fine-tuned for the task of keyphrase extraction. In the generative "},"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":"2112.08547","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T01:09:51Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"888aa96a7f99dacce0f1fe7791d5f05735cba6bb7faf66174da0e8c8628c88a3","abstract_canon_sha256":"d1853cbb3e8d0b3633251f25ca3b9436783ec34789e4282e1efd4c78fd120346"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:46.688382Z","signature_b64":"RsHWvMuGiWbXLf/BmlWMlCg3/qAv/eILsH8+MCImMkYMlfwSMk+ruuVHptKdeP47uwHwo7lw7xYEyWNpmLDmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37133148b8d5129422cdfa37e1d80e0f6577ad80e4ebb6246b6d2217abd72d19","last_reissued_at":"2026-07-05T04:38:46.687896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:46.687896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Rich Representation of Keyphrases from Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Debanjan Mahata, Mayank Kulkarni, Rajarshi Bhowmik, Ravneet Arora","submitted_at":"2021-12-16T01:09:51Z","abstract_excerpt":"In this work, we explore how to train task-specific language models aimed towards learning rich representation of keyphrases from text documents. We experiment with different masking strategies for pre-training transformer language models (LMs) in discriminative as well as generative settings. In the discriminative setting, we introduce a new pre-training objective - Keyphrase Boundary Infilling with Replacement (KBIR), showing large gains in performance (upto 8.16 points in F1) over SOTA, when the LM pre-trained using KBIR is fine-tuned for the task of keyphrase extraction. In the generative "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08547","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/2112.08547/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":"2112.08547","created_at":"2026-07-05T04:38:46.687963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08547v2","created_at":"2026-07-05T04:38:46.687963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08547","created_at":"2026-07-05T04:38:46.687963+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4JTCSFY2UJJ","created_at":"2026-07-05T04:38:46.687963+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4JTCSFY2UJJIIWN","created_at":"2026-07-05T04:38:46.687963+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4JTCSFY","created_at":"2026-07-05T04:38:46.687963+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/G4JTCSFY2UJJIIWN7I36DWAOB5","json":"https://pith.science/pith/G4JTCSFY2UJJIIWN7I36DWAOB5.json","graph_json":"https://pith.science/api/pith-number/G4JTCSFY2UJJIIWN7I36DWAOB5/graph.json","events_json":"https://pith.science/api/pith-number/G4JTCSFY2UJJIIWN7I36DWAOB5/events.json","paper":"https://pith.science/paper/G4JTCSFY"},"agent_actions":{"view_html":"https://pith.science/pith/G4JTCSFY2UJJIIWN7I36DWAOB5","download_json":"https://pith.science/pith/G4JTCSFY2UJJIIWN7I36DWAOB5.json","view_paper":"https://pith.science/paper/G4JTCSFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08547&json=true","fetch_graph":"https://pith.science/api/pith-number/G4JTCSFY2UJJIIWN7I36DWAOB5/graph.json","fetch_events":"https://pith.science/api/pith-number/G4JTCSFY2UJJIIWN7I36DWAOB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4JTCSFY2UJJIIWN7I36DWAOB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4JTCSFY2UJJIIWN7I36DWAOB5/action/storage_attestation","attest_author":"https://pith.science/pith/G4JTCSFY2UJJIIWN7I36DWAOB5/action/author_attestation","sign_citation":"https://pith.science/pith/G4JTCSFY2UJJIIWN7I36DWAOB5/action/citation_signature","submit_replication":"https://pith.science/pith/G4JTCSFY2UJJIIWN7I36DWAOB5/action/replication_record"}},"created_at":"2026-07-05T04:38:46.687963+00:00","updated_at":"2026-07-05T04:38:46.687963+00:00"}