{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QG67F745EMNRSII2QGEO35BW7R","short_pith_number":"pith:QG67F745","schema_version":"1.0","canonical_sha256":"81bdf2ff9d231b19211a8188edf436fc5eaf4239086ee86c0cf34c0bb5a959f6","source":{"kind":"arxiv","id":"2211.14320","version":2},"attestation_state":"computed","paper":{"title":"Bidirectional Representations for Low Resource Spoken Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hugo Van hamme, Marie-Francine Moens, Quentin Meeus","submitted_at":"2022-11-24T17:05:16Z","abstract_excerpt":"Most spoken language understanding systems use a pipeline approach composed of an automatic speech recognition interface and a natural language understanding module. This approach forces hard decisions when converting continuous inputs into discrete language symbols. Instead, we propose a representation model to encode speech in rich bidirectional encodings that can be used for downstream tasks such as intent prediction. The approach uses a masked language modelling objective to learn the representations, and thus benefits from both the left and right contexts. We show that the performance of "},"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":"2211.14320","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-24T17:05:16Z","cross_cats_sorted":[],"title_canon_sha256":"508706b4ec146784d45a037ec55356e25fafc6b8126e3248f1a4b9fe4ec9c7c3","abstract_canon_sha256":"498d61624ee998df879e9346eb661ed970053f1c93dc84e158f4a91f04dddab5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:38.138472Z","signature_b64":"IdVKDTHB2p5lRgUWsO+vpmfN1zX3Wk+ssmpzIEKrHTn6mAdhsMhlBDYH1hkDd/yd7nz0SAQTgnZhTBrLpPgiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81bdf2ff9d231b19211a8188edf436fc5eaf4239086ee86c0cf34c0bb5a959f6","last_reissued_at":"2026-07-05T07:01:38.137934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:38.137934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bidirectional Representations for Low Resource Spoken Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hugo Van hamme, Marie-Francine Moens, Quentin Meeus","submitted_at":"2022-11-24T17:05:16Z","abstract_excerpt":"Most spoken language understanding systems use a pipeline approach composed of an automatic speech recognition interface and a natural language understanding module. This approach forces hard decisions when converting continuous inputs into discrete language symbols. Instead, we propose a representation model to encode speech in rich bidirectional encodings that can be used for downstream tasks such as intent prediction. The approach uses a masked language modelling objective to learn the representations, and thus benefits from both the left and right contexts. We show that the performance of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.14320","kind":"arxiv","version":2},"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/2211.14320/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":"2211.14320","created_at":"2026-07-05T07:01:38.138044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.14320v2","created_at":"2026-07-05T07:01:38.138044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.14320","created_at":"2026-07-05T07:01:38.138044+00:00"},{"alias_kind":"pith_short_12","alias_value":"QG67F745EMNR","created_at":"2026-07-05T07:01:38.138044+00:00"},{"alias_kind":"pith_short_16","alias_value":"QG67F745EMNRSII2","created_at":"2026-07-05T07:01:38.138044+00:00"},{"alias_kind":"pith_short_8","alias_value":"QG67F745","created_at":"2026-07-05T07:01:38.138044+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/QG67F745EMNRSII2QGEO35BW7R","json":"https://pith.science/pith/QG67F745EMNRSII2QGEO35BW7R.json","graph_json":"https://pith.science/api/pith-number/QG67F745EMNRSII2QGEO35BW7R/graph.json","events_json":"https://pith.science/api/pith-number/QG67F745EMNRSII2QGEO35BW7R/events.json","paper":"https://pith.science/paper/QG67F745"},"agent_actions":{"view_html":"https://pith.science/pith/QG67F745EMNRSII2QGEO35BW7R","download_json":"https://pith.science/pith/QG67F745EMNRSII2QGEO35BW7R.json","view_paper":"https://pith.science/paper/QG67F745","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.14320&json=true","fetch_graph":"https://pith.science/api/pith-number/QG67F745EMNRSII2QGEO35BW7R/graph.json","fetch_events":"https://pith.science/api/pith-number/QG67F745EMNRSII2QGEO35BW7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QG67F745EMNRSII2QGEO35BW7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QG67F745EMNRSII2QGEO35BW7R/action/storage_attestation","attest_author":"https://pith.science/pith/QG67F745EMNRSII2QGEO35BW7R/action/author_attestation","sign_citation":"https://pith.science/pith/QG67F745EMNRSII2QGEO35BW7R/action/citation_signature","submit_replication":"https://pith.science/pith/QG67F745EMNRSII2QGEO35BW7R/action/replication_record"}},"created_at":"2026-07-05T07:01:38.138044+00:00","updated_at":"2026-07-05T07:01:38.138044+00:00"}