{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:F4GXED6FAFHVZDLK6TGR7QQ3QJ","short_pith_number":"pith:F4GXED6F","schema_version":"1.0","canonical_sha256":"2f0d720fc5014f5c8d6af4cd1fc21b826d75590c4a800f19d8e9b48820aafc7b","source":{"kind":"arxiv","id":"2104.08268","version":1},"attestation_state":"computed","paper":{"title":"Data Augmentation for Voice-Assistant NLU using BERT-based Interchangeable Rephrase","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Akhila Yerukola, Hongxia Jin, Mason Bretan","submitted_at":"2021-04-16T17:53:58Z","abstract_excerpt":"We introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method with a range of augmentation techniques encompassing generative models such as VAEs and performance-boosting techniques such as synonym replacement and back-translation. We show our method performs strongly on domain and intent classification tasks for a voice assistant and in a user-study focused on utterance naturalness and semantic similarity."},"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":"2104.08268","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-16T17:53:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7215c354622a86e02b2d56084922a658af982485cb99bc76314fbf1382cff34f","abstract_canon_sha256":"c3a401ed61b6b265ea2b94834956c5bafe7909fdc5b1370c17fa92f0ad2ebb9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:42.610916Z","signature_b64":"JhkUdtugCEN/w7kbOPWgwCGlW3tpYcDs7fp5vBbDK7JRxBjfkqDT/TxWrhnLYZxMwCE4ZngGaqm5XJ46tzoCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f0d720fc5014f5c8d6af4cd1fc21b826d75590c4a800f19d8e9b48820aafc7b","last_reissued_at":"2026-07-05T02:32:42.610447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:42.610447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Augmentation for Voice-Assistant NLU using BERT-based Interchangeable Rephrase","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Akhila Yerukola, Hongxia Jin, Mason Bretan","submitted_at":"2021-04-16T17:53:58Z","abstract_excerpt":"We introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method with a range of augmentation techniques encompassing generative models such as VAEs and performance-boosting techniques such as synonym replacement and back-translation. We show our method performs strongly on domain and intent classification tasks for a voice assistant and in a user-study focused on utterance naturalness and semantic similarity."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08268","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/2104.08268/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":"2104.08268","created_at":"2026-07-05T02:32:42.610506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.08268v1","created_at":"2026-07-05T02:32:42.610506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08268","created_at":"2026-07-05T02:32:42.610506+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4GXED6FAFHV","created_at":"2026-07-05T02:32:42.610506+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4GXED6FAFHVZDLK","created_at":"2026-07-05T02:32:42.610506+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4GXED6F","created_at":"2026-07-05T02:32:42.610506+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/F4GXED6FAFHVZDLK6TGR7QQ3QJ","json":"https://pith.science/pith/F4GXED6FAFHVZDLK6TGR7QQ3QJ.json","graph_json":"https://pith.science/api/pith-number/F4GXED6FAFHVZDLK6TGR7QQ3QJ/graph.json","events_json":"https://pith.science/api/pith-number/F4GXED6FAFHVZDLK6TGR7QQ3QJ/events.json","paper":"https://pith.science/paper/F4GXED6F"},"agent_actions":{"view_html":"https://pith.science/pith/F4GXED6FAFHVZDLK6TGR7QQ3QJ","download_json":"https://pith.science/pith/F4GXED6FAFHVZDLK6TGR7QQ3QJ.json","view_paper":"https://pith.science/paper/F4GXED6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.08268&json=true","fetch_graph":"https://pith.science/api/pith-number/F4GXED6FAFHVZDLK6TGR7QQ3QJ/graph.json","fetch_events":"https://pith.science/api/pith-number/F4GXED6FAFHVZDLK6TGR7QQ3QJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4GXED6FAFHVZDLK6TGR7QQ3QJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4GXED6FAFHVZDLK6TGR7QQ3QJ/action/storage_attestation","attest_author":"https://pith.science/pith/F4GXED6FAFHVZDLK6TGR7QQ3QJ/action/author_attestation","sign_citation":"https://pith.science/pith/F4GXED6FAFHVZDLK6TGR7QQ3QJ/action/citation_signature","submit_replication":"https://pith.science/pith/F4GXED6FAFHVZDLK6TGR7QQ3QJ/action/replication_record"}},"created_at":"2026-07-05T02:32:42.610506+00:00","updated_at":"2026-07-05T02:32:42.610506+00:00"}