{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CUXXUWSGBONW2SLWDJQCIGEC4K","short_pith_number":"pith:CUXXUWSG","schema_version":"1.0","canonical_sha256":"152f7a5a460b9b6d49761a60241882e288c99238062f92614b11da0506bc17fe","source":{"kind":"arxiv","id":"2010.00910","version":1},"attestation_state":"computed","paper":{"title":"Continual Learning for Natural Language Generation in Task-oriented Dialog Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Boi Faltings, Fei Mi, Liangwei Chen, Mengjie Zhao, Minlie Huang","submitted_at":"2020-10-02T10:32:29Z","abstract_excerpt":"Natural language generation (NLG) is an essential component of task-oriented dialog systems. Despite the recent success of neural approaches for NLG, they are typically developed in an offline manner for particular domains. To better fit real-life applications where new data come in a stream, we study NLG in a \"continual learning\" setting to expand its knowledge to new domains or functionalities incrementally. The major challenge towards this goal is catastrophic forgetting, meaning that a continually trained model tends to forget the knowledge it has learned before. To this end, we propose a "},"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":"2010.00910","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-02T10:32:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"409c8404bcf945cadae0eb636125f57a72d2db6daa326a7c78161fb26fc65652","abstract_canon_sha256":"186c00cffdb678e0309189edf17f64a6f09a839533e4be43905cef3e382a0ff5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:48.822254Z","signature_b64":"qkstQtUU2ZJ8XEEOomdVHq5covl7Q3rsHPYqDZsREnORwzYrhQrucTwUY+kmWlDLU71krCD3Em3mZ0fnpln6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"152f7a5a460b9b6d49761a60241882e288c99238062f92614b11da0506bc17fe","last_reissued_at":"2026-07-05T01:39:48.821779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:48.821779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning for Natural Language Generation in Task-oriented Dialog Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Boi Faltings, Fei Mi, Liangwei Chen, Mengjie Zhao, Minlie Huang","submitted_at":"2020-10-02T10:32:29Z","abstract_excerpt":"Natural language generation (NLG) is an essential component of task-oriented dialog systems. Despite the recent success of neural approaches for NLG, they are typically developed in an offline manner for particular domains. To better fit real-life applications where new data come in a stream, we study NLG in a \"continual learning\" setting to expand its knowledge to new domains or functionalities incrementally. The major challenge towards this goal is catastrophic forgetting, meaning that a continually trained model tends to forget the knowledge it has learned before. To this end, we propose a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.00910","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/2010.00910/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":"2010.00910","created_at":"2026-07-05T01:39:48.821839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.00910v1","created_at":"2026-07-05T01:39:48.821839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.00910","created_at":"2026-07-05T01:39:48.821839+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUXXUWSGBONW","created_at":"2026-07-05T01:39:48.821839+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUXXUWSGBONW2SLW","created_at":"2026-07-05T01:39:48.821839+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUXXUWSG","created_at":"2026-07-05T01:39:48.821839+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13045","citing_title":"Continual Learning for Generative AI: From LLMs to MLLMs and Beyond","ref_index":154,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUXXUWSGBONW2SLWDJQCIGEC4K","json":"https://pith.science/pith/CUXXUWSGBONW2SLWDJQCIGEC4K.json","graph_json":"https://pith.science/api/pith-number/CUXXUWSGBONW2SLWDJQCIGEC4K/graph.json","events_json":"https://pith.science/api/pith-number/CUXXUWSGBONW2SLWDJQCIGEC4K/events.json","paper":"https://pith.science/paper/CUXXUWSG"},"agent_actions":{"view_html":"https://pith.science/pith/CUXXUWSGBONW2SLWDJQCIGEC4K","download_json":"https://pith.science/pith/CUXXUWSGBONW2SLWDJQCIGEC4K.json","view_paper":"https://pith.science/paper/CUXXUWSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.00910&json=true","fetch_graph":"https://pith.science/api/pith-number/CUXXUWSGBONW2SLWDJQCIGEC4K/graph.json","fetch_events":"https://pith.science/api/pith-number/CUXXUWSGBONW2SLWDJQCIGEC4K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUXXUWSGBONW2SLWDJQCIGEC4K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUXXUWSGBONW2SLWDJQCIGEC4K/action/storage_attestation","attest_author":"https://pith.science/pith/CUXXUWSGBONW2SLWDJQCIGEC4K/action/author_attestation","sign_citation":"https://pith.science/pith/CUXXUWSGBONW2SLWDJQCIGEC4K/action/citation_signature","submit_replication":"https://pith.science/pith/CUXXUWSGBONW2SLWDJQCIGEC4K/action/replication_record"}},"created_at":"2026-07-05T01:39:48.821839+00:00","updated_at":"2026-07-05T01:39:48.821839+00:00"}