{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SCIHQY4HWE5BJMBI62AGO2PGHW","short_pith_number":"pith:SCIHQY4H","schema_version":"1.0","canonical_sha256":"9090786387b13a14b028f6806769e63d9e7285dcbf5b8f6b007a771b1780a49f","source":{"kind":"arxiv","id":"1909.00556","version":1},"attestation_state":"computed","paper":{"title":"Phrase-Level Class based Language Model for Mandarin Smart Speaker Query Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Su, Guangsen Wang, Lei Han, Liqiang He, Yiheng Huang","submitted_at":"2019-09-02T05:55:36Z","abstract_excerpt":"The success of speech assistants requires precise recognition of a number of entities on particular contexts. A common solution is to train a class-based n-gram language model and then expand the classes into specific words or phrases. However, when the class has a huge list, e.g., more than 20 million songs, a fully expansion will cause memory explosion. Worse still, the list items in the class need to be updated frequently, which requires a dynamic model updating technique. In this work, we propose to train pruned language models for the word classes to replace the slots in the root n-gram. "},"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":"1909.00556","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-02T05:55:36Z","cross_cats_sorted":[],"title_canon_sha256":"b646ae6d77d603e1db323caad43f1075b96939670307cef294c0f506d1d58387","abstract_canon_sha256":"b8370ca8019b60688ad0595a8eb18144187d4c97a4f13d121e27fcd2a5f210de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:01:10.781028Z","signature_b64":"McLeOjkUCCr5PpzVsYsoKH8NMrT2c93Gs0wx8BJtZLABRtclA4gTgLf2QyC6Luqu1ZA2f3aWchiH2LeTb8reCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9090786387b13a14b028f6806769e63d9e7285dcbf5b8f6b007a771b1780a49f","last_reissued_at":"2026-07-05T00:01:10.780657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:01:10.780657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phrase-Level Class based Language Model for Mandarin Smart Speaker Query Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Su, Guangsen Wang, Lei Han, Liqiang He, Yiheng Huang","submitted_at":"2019-09-02T05:55:36Z","abstract_excerpt":"The success of speech assistants requires precise recognition of a number of entities on particular contexts. A common solution is to train a class-based n-gram language model and then expand the classes into specific words or phrases. However, when the class has a huge list, e.g., more than 20 million songs, a fully expansion will cause memory explosion. Worse still, the list items in the class need to be updated frequently, which requires a dynamic model updating technique. In this work, we propose to train pruned language models for the word classes to replace the slots in the root n-gram. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00556","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/1909.00556/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":"1909.00556","created_at":"2026-07-05T00:01:10.780714+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.00556v1","created_at":"2026-07-05T00:01:10.780714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00556","created_at":"2026-07-05T00:01:10.780714+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCIHQY4HWE5B","created_at":"2026-07-05T00:01:10.780714+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCIHQY4HWE5BJMBI","created_at":"2026-07-05T00:01:10.780714+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCIHQY4H","created_at":"2026-07-05T00:01:10.780714+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/SCIHQY4HWE5BJMBI62AGO2PGHW","json":"https://pith.science/pith/SCIHQY4HWE5BJMBI62AGO2PGHW.json","graph_json":"https://pith.science/api/pith-number/SCIHQY4HWE5BJMBI62AGO2PGHW/graph.json","events_json":"https://pith.science/api/pith-number/SCIHQY4HWE5BJMBI62AGO2PGHW/events.json","paper":"https://pith.science/paper/SCIHQY4H"},"agent_actions":{"view_html":"https://pith.science/pith/SCIHQY4HWE5BJMBI62AGO2PGHW","download_json":"https://pith.science/pith/SCIHQY4HWE5BJMBI62AGO2PGHW.json","view_paper":"https://pith.science/paper/SCIHQY4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.00556&json=true","fetch_graph":"https://pith.science/api/pith-number/SCIHQY4HWE5BJMBI62AGO2PGHW/graph.json","fetch_events":"https://pith.science/api/pith-number/SCIHQY4HWE5BJMBI62AGO2PGHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCIHQY4HWE5BJMBI62AGO2PGHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCIHQY4HWE5BJMBI62AGO2PGHW/action/storage_attestation","attest_author":"https://pith.science/pith/SCIHQY4HWE5BJMBI62AGO2PGHW/action/author_attestation","sign_citation":"https://pith.science/pith/SCIHQY4HWE5BJMBI62AGO2PGHW/action/citation_signature","submit_replication":"https://pith.science/pith/SCIHQY4HWE5BJMBI62AGO2PGHW/action/replication_record"}},"created_at":"2026-07-05T00:01:10.780714+00:00","updated_at":"2026-07-05T00:01:10.780714+00:00"}