{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LNUKQ6VT75TTLV2Q7N5HMJBULP","short_pith_number":"pith:LNUKQ6VT","schema_version":"1.0","canonical_sha256":"5b68a87ab3ff6735d750fb7a7624345bd851b631256900eb9f02cdcab8f3a0c0","source":{"kind":"arxiv","id":"2012.11468","version":1},"attestation_state":"computed","paper":{"title":"Pattern-aware Data Augmentation for Query Rewriting in Voice Assistant Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenlei Guo, Fan Yang, Sixing Lu, Xiaojiang Huang, Xing Fan, Yunmo Chen","submitted_at":"2020-12-21T16:36:32Z","abstract_excerpt":"Query rewriting (QR) systems are widely used to reduce the friction caused by errors in a spoken language understanding pipeline. However, the underlying supervised models require a large number of labeled pairs, and these pairs are hard and costly to be collected. Therefore, We propose an augmentation framework that learns patterns from existing training pairs and generates rewrite candidates from rewrite labels inversely to compensate for insufficient QR training data. The proposed framework casts the augmentation problem as a sequence-to-sequence generation task and enforces the optimizatio"},"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":"2012.11468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-21T16:36:32Z","cross_cats_sorted":[],"title_canon_sha256":"fac32c680c89ff24229bd0d1bbc3f7d8f4a9f99c940fc8f83e7f669ece7f43f1","abstract_canon_sha256":"d01bd38e496b02b24691b7eb71ed4d68a91c9824bdeed521979619c2d74388f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:01:02.138065Z","signature_b64":"+g480LNMq5n8L9kEzFvDhCkS4WbDJ0AswyXWbCxiRsfhSl2c08FhUs0006wV1Z/x2LqsQKMuyJh3qQ2PsQDYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b68a87ab3ff6735d750fb7a7624345bd851b631256900eb9f02cdcab8f3a0c0","last_reissued_at":"2026-07-05T02:01:02.137592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:01:02.137592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pattern-aware Data Augmentation for Query Rewriting in Voice Assistant Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenlei Guo, Fan Yang, Sixing Lu, Xiaojiang Huang, Xing Fan, Yunmo Chen","submitted_at":"2020-12-21T16:36:32Z","abstract_excerpt":"Query rewriting (QR) systems are widely used to reduce the friction caused by errors in a spoken language understanding pipeline. However, the underlying supervised models require a large number of labeled pairs, and these pairs are hard and costly to be collected. Therefore, We propose an augmentation framework that learns patterns from existing training pairs and generates rewrite candidates from rewrite labels inversely to compensate for insufficient QR training data. The proposed framework casts the augmentation problem as a sequence-to-sequence generation task and enforces the optimizatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11468","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/2012.11468/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":"2012.11468","created_at":"2026-07-05T02:01:02.137644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.11468v1","created_at":"2026-07-05T02:01:02.137644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11468","created_at":"2026-07-05T02:01:02.137644+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNUKQ6VT75TT","created_at":"2026-07-05T02:01:02.137644+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNUKQ6VT75TTLV2Q","created_at":"2026-07-05T02:01:02.137644+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNUKQ6VT","created_at":"2026-07-05T02:01:02.137644+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/LNUKQ6VT75TTLV2Q7N5HMJBULP","json":"https://pith.science/pith/LNUKQ6VT75TTLV2Q7N5HMJBULP.json","graph_json":"https://pith.science/api/pith-number/LNUKQ6VT75TTLV2Q7N5HMJBULP/graph.json","events_json":"https://pith.science/api/pith-number/LNUKQ6VT75TTLV2Q7N5HMJBULP/events.json","paper":"https://pith.science/paper/LNUKQ6VT"},"agent_actions":{"view_html":"https://pith.science/pith/LNUKQ6VT75TTLV2Q7N5HMJBULP","download_json":"https://pith.science/pith/LNUKQ6VT75TTLV2Q7N5HMJBULP.json","view_paper":"https://pith.science/paper/LNUKQ6VT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.11468&json=true","fetch_graph":"https://pith.science/api/pith-number/LNUKQ6VT75TTLV2Q7N5HMJBULP/graph.json","fetch_events":"https://pith.science/api/pith-number/LNUKQ6VT75TTLV2Q7N5HMJBULP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNUKQ6VT75TTLV2Q7N5HMJBULP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNUKQ6VT75TTLV2Q7N5HMJBULP/action/storage_attestation","attest_author":"https://pith.science/pith/LNUKQ6VT75TTLV2Q7N5HMJBULP/action/author_attestation","sign_citation":"https://pith.science/pith/LNUKQ6VT75TTLV2Q7N5HMJBULP/action/citation_signature","submit_replication":"https://pith.science/pith/LNUKQ6VT75TTLV2Q7N5HMJBULP/action/replication_record"}},"created_at":"2026-07-05T02:01:02.137644+00:00","updated_at":"2026-07-05T02:01:02.137644+00:00"}