{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3NM3N4DF6CLK4BO3X2UVVLE6CC","short_pith_number":"pith:3NM3N4DF","schema_version":"1.0","canonical_sha256":"db59b6f065f096ae05dbbea95aac9e1088577a459e8728009880e649bb65ebc0","source":{"kind":"arxiv","id":"2004.09936","version":3},"attestation_state":"computed","paper":{"title":"DIET: Lightweight Language Understanding for Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan Nichol, Daksh Varshneya, Tanja Bunk, Vladimir Vlasov","submitted_at":"2020-04-21T12:10:48Z","abstract_excerpt":"Large-scale pre-trained language models have shown impressive results on language understanding benchmarks like GLUE and SuperGLUE, improving considerably over other pre-training methods like distributed representations (GloVe) and purely supervised approaches. We introduce the Dual Intent and Entity Transformer (DIET) architecture, and study the effectiveness of different pre-trained representations on intent and entity prediction, two common dialogue language understanding tasks. DIET advances the state of the art on a complex multi-domain NLU dataset and achieves similarly high performance "},"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":"2004.09936","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-21T12:10:48Z","cross_cats_sorted":[],"title_canon_sha256":"03bb916825e056d9ab5434bfd1b7113c4dcb372a22f60694e5fff45f2266fd5a","abstract_canon_sha256":"f55f820f93779d6acc8fdf7563cea601bbbfc5ff4fdc04ed785073a36388a2a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:40.341550Z","signature_b64":"NdWBP8U55om4ISjHZzSyECxUcNooGXpKFlkZslQrRXmvPDBAe13/R38Gr1TWTmFwP2tVW7YmK2HbBK1FKbTiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db59b6f065f096ae05dbbea95aac9e1088577a459e8728009880e649bb65ebc0","last_reissued_at":"2026-07-05T01:01:40.341111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:40.341111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIET: Lightweight Language Understanding for Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan Nichol, Daksh Varshneya, Tanja Bunk, Vladimir Vlasov","submitted_at":"2020-04-21T12:10:48Z","abstract_excerpt":"Large-scale pre-trained language models have shown impressive results on language understanding benchmarks like GLUE and SuperGLUE, improving considerably over other pre-training methods like distributed representations (GloVe) and purely supervised approaches. We introduce the Dual Intent and Entity Transformer (DIET) architecture, and study the effectiveness of different pre-trained representations on intent and entity prediction, two common dialogue language understanding tasks. DIET advances the state of the art on a complex multi-domain NLU dataset and achieves similarly high performance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.09936","kind":"arxiv","version":3},"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/2004.09936/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":"2004.09936","created_at":"2026-07-05T01:01:40.341167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.09936v3","created_at":"2026-07-05T01:01:40.341167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.09936","created_at":"2026-07-05T01:01:40.341167+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NM3N4DF6CLK","created_at":"2026-07-05T01:01:40.341167+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NM3N4DF6CLK4BO3","created_at":"2026-07-05T01:01:40.341167+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NM3N4DF","created_at":"2026-07-05T01:01:40.341167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10241","citing_title":"Building Korean linguistic resource for NLU data generation of banking app CS dialog system","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07432","citing_title":"Generating training datasets for legal chatbots in Korean","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NM3N4DF6CLK4BO3X2UVVLE6CC","json":"https://pith.science/pith/3NM3N4DF6CLK4BO3X2UVVLE6CC.json","graph_json":"https://pith.science/api/pith-number/3NM3N4DF6CLK4BO3X2UVVLE6CC/graph.json","events_json":"https://pith.science/api/pith-number/3NM3N4DF6CLK4BO3X2UVVLE6CC/events.json","paper":"https://pith.science/paper/3NM3N4DF"},"agent_actions":{"view_html":"https://pith.science/pith/3NM3N4DF6CLK4BO3X2UVVLE6CC","download_json":"https://pith.science/pith/3NM3N4DF6CLK4BO3X2UVVLE6CC.json","view_paper":"https://pith.science/paper/3NM3N4DF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.09936&json=true","fetch_graph":"https://pith.science/api/pith-number/3NM3N4DF6CLK4BO3X2UVVLE6CC/graph.json","fetch_events":"https://pith.science/api/pith-number/3NM3N4DF6CLK4BO3X2UVVLE6CC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NM3N4DF6CLK4BO3X2UVVLE6CC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NM3N4DF6CLK4BO3X2UVVLE6CC/action/storage_attestation","attest_author":"https://pith.science/pith/3NM3N4DF6CLK4BO3X2UVVLE6CC/action/author_attestation","sign_citation":"https://pith.science/pith/3NM3N4DF6CLK4BO3X2UVVLE6CC/action/citation_signature","submit_replication":"https://pith.science/pith/3NM3N4DF6CLK4BO3X2UVVLE6CC/action/replication_record"}},"created_at":"2026-07-05T01:01:40.341167+00:00","updated_at":"2026-07-05T01:01:40.341167+00:00"}