{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3Q2AMNGJTDLAHC56BJQBLPYK5G","short_pith_number":"pith:3Q2AMNGJ","schema_version":"1.0","canonical_sha256":"dc340634c998d6038bbe0a6015bf0ae99be8e2fb402d3f4c031c41de14db3d7e","source":{"kind":"arxiv","id":"2005.08866","version":2},"attestation_state":"computed","paper":{"title":"Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniela Gerz, Ivan Vuli\\'c, Matthew Henderson, Sam Coope, Tyler Farghly","submitted_at":"2020-05-18T16:40:30Z","abstract_excerpt":"We introduce Span-ConveRT, a light-weight model for dialog slot-filling which frames the task as a turn-based span extraction task. This formulation allows for a simple integration of conversational knowledge coded in large pretrained conversational models such as ConveRT (Henderson et al., 2019). We show that leveraging such knowledge in Span-ConveRT is especially useful for few-shot learning scenarios: we report consistent gains over 1) a span extractor that trains representations from scratch in the target domain, and 2) a BERT-based span extractor. In order to inspire more work on span ext"},"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":"2005.08866","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-18T16:40:30Z","cross_cats_sorted":[],"title_canon_sha256":"443aab608fee720a1f1b1eb7b7d6f279637852f6b125003465be44ba8f31a7f6","abstract_canon_sha256":"165187ee83b63b1913576111293592cb9dae325b24ee2fb38f427b8411721c89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:19:39.977488Z","signature_b64":"pg9ir9w9omoNOABarQFhcX/mmoc40fXYJYLLTnxi8VwKwZz8I/uz47YNDlEU7iVemXjbx3YOshwSQOnRO8p4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc340634c998d6038bbe0a6015bf0ae99be8e2fb402d3f4c031c41de14db3d7e","last_reissued_at":"2026-07-05T01:19:39.976975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:19:39.976975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniela Gerz, Ivan Vuli\\'c, Matthew Henderson, Sam Coope, Tyler Farghly","submitted_at":"2020-05-18T16:40:30Z","abstract_excerpt":"We introduce Span-ConveRT, a light-weight model for dialog slot-filling which frames the task as a turn-based span extraction task. This formulation allows for a simple integration of conversational knowledge coded in large pretrained conversational models such as ConveRT (Henderson et al., 2019). We show that leveraging such knowledge in Span-ConveRT is especially useful for few-shot learning scenarios: we report consistent gains over 1) a span extractor that trains representations from scratch in the target domain, and 2) a BERT-based span extractor. In order to inspire more work on span ext"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08866","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/2005.08866/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":"2005.08866","created_at":"2026-07-05T01:19:39.977036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.08866v2","created_at":"2026-07-05T01:19:39.977036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08866","created_at":"2026-07-05T01:19:39.977036+00:00"},{"alias_kind":"pith_short_12","alias_value":"3Q2AMNGJTDLA","created_at":"2026-07-05T01:19:39.977036+00:00"},{"alias_kind":"pith_short_16","alias_value":"3Q2AMNGJTDLAHC56","created_at":"2026-07-05T01:19:39.977036+00:00"},{"alias_kind":"pith_short_8","alias_value":"3Q2AMNGJ","created_at":"2026-07-05T01:19:39.977036+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/3Q2AMNGJTDLAHC56BJQBLPYK5G","json":"https://pith.science/pith/3Q2AMNGJTDLAHC56BJQBLPYK5G.json","graph_json":"https://pith.science/api/pith-number/3Q2AMNGJTDLAHC56BJQBLPYK5G/graph.json","events_json":"https://pith.science/api/pith-number/3Q2AMNGJTDLAHC56BJQBLPYK5G/events.json","paper":"https://pith.science/paper/3Q2AMNGJ"},"agent_actions":{"view_html":"https://pith.science/pith/3Q2AMNGJTDLAHC56BJQBLPYK5G","download_json":"https://pith.science/pith/3Q2AMNGJTDLAHC56BJQBLPYK5G.json","view_paper":"https://pith.science/paper/3Q2AMNGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.08866&json=true","fetch_graph":"https://pith.science/api/pith-number/3Q2AMNGJTDLAHC56BJQBLPYK5G/graph.json","fetch_events":"https://pith.science/api/pith-number/3Q2AMNGJTDLAHC56BJQBLPYK5G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3Q2AMNGJTDLAHC56BJQBLPYK5G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3Q2AMNGJTDLAHC56BJQBLPYK5G/action/storage_attestation","attest_author":"https://pith.science/pith/3Q2AMNGJTDLAHC56BJQBLPYK5G/action/author_attestation","sign_citation":"https://pith.science/pith/3Q2AMNGJTDLAHC56BJQBLPYK5G/action/citation_signature","submit_replication":"https://pith.science/pith/3Q2AMNGJTDLAHC56BJQBLPYK5G/action/replication_record"}},"created_at":"2026-07-05T01:19:39.977036+00:00","updated_at":"2026-07-05T01:19:39.977036+00:00"}