{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6QJQM2LF5QUARUQJQQOER4PINO","short_pith_number":"pith:6QJQM2LF","schema_version":"1.0","canonical_sha256":"f413066965ec2808d209841c48f1e86b91c3e9d6d0a9708822127e7708b80fa3","source":{"kind":"arxiv","id":"2010.10998","version":2},"attestation_state":"computed","paper":{"title":"Open-Domain Frame Semantic Parsing Using Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditya Kalyanpur, Ariel Diertani, Jennifer Chu-Carroll, Mark Sammons, Or Biran, Owen Rambow, Tom Breloff","submitted_at":"2020-10-21T13:38:04Z","abstract_excerpt":"Frame semantic parsing is a complex problem which includes multiple underlying subtasks. Recent approaches have employed joint learning of subtasks (such as predicate and argument detection), and multi-task learning of related tasks (such as syntactic and semantic parsing). In this paper, we explore multi-task learning of all subtasks with transformer-based models. We show that a purely generative encoder-decoder architecture handily beats the previous state of the art in FrameNet 1.7 parsing, and that a mixed decoding multi-task approach achieves even better performance. Finally, we show that"},"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":"2010.10998","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-21T13:38:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"350e41171f7f404458851fc98331a473ca0df6c34297f2f28da46550822bd032","abstract_canon_sha256":"256c31f07739604e53aabcf47294827ef5aa98a7ef59e5232b75ea7c5b1afd05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:45.853087Z","signature_b64":"slrB1aFztm4CAW0+Pg42cCtpW+VeN7cCQB944xboP1TMTSko9zStwM/eaedCqAM9jC+byKM7f3DptRRNUdqRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f413066965ec2808d209841c48f1e86b91c3e9d6d0a9708822127e7708b80fa3","last_reissued_at":"2026-07-05T01:45:45.852747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:45.852747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Domain Frame Semantic Parsing Using Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditya Kalyanpur, Ariel Diertani, Jennifer Chu-Carroll, Mark Sammons, Or Biran, Owen Rambow, Tom Breloff","submitted_at":"2020-10-21T13:38:04Z","abstract_excerpt":"Frame semantic parsing is a complex problem which includes multiple underlying subtasks. Recent approaches have employed joint learning of subtasks (such as predicate and argument detection), and multi-task learning of related tasks (such as syntactic and semantic parsing). In this paper, we explore multi-task learning of all subtasks with transformer-based models. We show that a purely generative encoder-decoder architecture handily beats the previous state of the art in FrameNet 1.7 parsing, and that a mixed decoding multi-task approach achieves even better performance. Finally, we show that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10998","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/2010.10998/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":"2010.10998","created_at":"2026-07-05T01:45:45.852798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.10998v2","created_at":"2026-07-05T01:45:45.852798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10998","created_at":"2026-07-05T01:45:45.852798+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QJQM2LF5QUA","created_at":"2026-07-05T01:45:45.852798+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QJQM2LF5QUARUQJ","created_at":"2026-07-05T01:45:45.852798+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QJQM2LF","created_at":"2026-07-05T01:45:45.852798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10421","citing_title":"Beyond the Battlefield: Framing Analysis of Media Coverage in Conflict Reporting","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6QJQM2LF5QUARUQJQQOER4PINO","json":"https://pith.science/pith/6QJQM2LF5QUARUQJQQOER4PINO.json","graph_json":"https://pith.science/api/pith-number/6QJQM2LF5QUARUQJQQOER4PINO/graph.json","events_json":"https://pith.science/api/pith-number/6QJQM2LF5QUARUQJQQOER4PINO/events.json","paper":"https://pith.science/paper/6QJQM2LF"},"agent_actions":{"view_html":"https://pith.science/pith/6QJQM2LF5QUARUQJQQOER4PINO","download_json":"https://pith.science/pith/6QJQM2LF5QUARUQJQQOER4PINO.json","view_paper":"https://pith.science/paper/6QJQM2LF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.10998&json=true","fetch_graph":"https://pith.science/api/pith-number/6QJQM2LF5QUARUQJQQOER4PINO/graph.json","fetch_events":"https://pith.science/api/pith-number/6QJQM2LF5QUARUQJQQOER4PINO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QJQM2LF5QUARUQJQQOER4PINO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QJQM2LF5QUARUQJQQOER4PINO/action/storage_attestation","attest_author":"https://pith.science/pith/6QJQM2LF5QUARUQJQQOER4PINO/action/author_attestation","sign_citation":"https://pith.science/pith/6QJQM2LF5QUARUQJQQOER4PINO/action/citation_signature","submit_replication":"https://pith.science/pith/6QJQM2LF5QUARUQJQQOER4PINO/action/replication_record"}},"created_at":"2026-07-05T01:45:45.852798+00:00","updated_at":"2026-07-05T01:45:45.852798+00:00"}