{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UNI3DQHO3NRRJFSEFBYIE2CRXZ","short_pith_number":"pith:UNI3DQHO","schema_version":"1.0","canonical_sha256":"a351b1c0eedb631496442870826851be4ca3ed9c20e404b96545c8c7323d1c74","source":{"kind":"arxiv","id":"2404.02588","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models for Expansion of Spoken Language Understanding Systems to New Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Artur Janicki, Jakub Hoscilowicz, Marcin Skorupa, Marcin Sowa\\'nski, Pawel Pawlowski","submitted_at":"2024-04-03T09:13:26Z","abstract_excerpt":"Spoken Language Understanding (SLU) models are a core component of voice assistants (VA), such as Alexa, Bixby, and Google Assistant. In this paper, we introduce a pipeline designed to extend SLU systems to new languages, utilizing Large Language Models (LLMs) that we fine-tune for machine translation of slot-annotated SLU training data. Our approach improved on the MultiATIS++ benchmark, a primary multi-language SLU dataset, in the cloud scenario using an mBERT model. Specifically, we saw an improvement in the Overall Accuracy metric: from 53% to 62.18%, compared to the existing state-of-the-"},"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":"2404.02588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T09:13:26Z","cross_cats_sorted":[],"title_canon_sha256":"5bab5632eab2f7c08568ff8839f606299655c699e27e0c7129bf0c263e1ca17b","abstract_canon_sha256":"720dffe6f2fa4e6e95273a56bd4762eda34553ad6573f2a490f98297f8fedcf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:58.660693Z","signature_b64":"2u6MJdyTKh0RBAt1ohcrJAAU7Rx/KlxV0kabxpGK0VgV+7rymr/ocTFsG68suaXfXVbmbzTheDrGj6t2cdIrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a351b1c0eedb631496442870826851be4ca3ed9c20e404b96545c8c7323d1c74","last_reissued_at":"2026-07-05T08:03:58.660263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:58.660263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models for Expansion of Spoken Language Understanding Systems to New Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Artur Janicki, Jakub Hoscilowicz, Marcin Skorupa, Marcin Sowa\\'nski, Pawel Pawlowski","submitted_at":"2024-04-03T09:13:26Z","abstract_excerpt":"Spoken Language Understanding (SLU) models are a core component of voice assistants (VA), such as Alexa, Bixby, and Google Assistant. In this paper, we introduce a pipeline designed to extend SLU systems to new languages, utilizing Large Language Models (LLMs) that we fine-tune for machine translation of slot-annotated SLU training data. Our approach improved on the MultiATIS++ benchmark, a primary multi-language SLU dataset, in the cloud scenario using an mBERT model. Specifically, we saw an improvement in the Overall Accuracy metric: from 53% to 62.18%, compared to the existing state-of-the-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02588","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/2404.02588/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":"2404.02588","created_at":"2026-07-05T08:03:58.660337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02588v1","created_at":"2026-07-05T08:03:58.660337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02588","created_at":"2026-07-05T08:03:58.660337+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNI3DQHO3NRR","created_at":"2026-07-05T08:03:58.660337+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNI3DQHO3NRRJFSE","created_at":"2026-07-05T08:03:58.660337+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNI3DQHO","created_at":"2026-07-05T08:03:58.660337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08970","citing_title":"Reasoning-Aware Query-Focused Summarization over Multi-Table Data","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNI3DQHO3NRRJFSEFBYIE2CRXZ","json":"https://pith.science/pith/UNI3DQHO3NRRJFSEFBYIE2CRXZ.json","graph_json":"https://pith.science/api/pith-number/UNI3DQHO3NRRJFSEFBYIE2CRXZ/graph.json","events_json":"https://pith.science/api/pith-number/UNI3DQHO3NRRJFSEFBYIE2CRXZ/events.json","paper":"https://pith.science/paper/UNI3DQHO"},"agent_actions":{"view_html":"https://pith.science/pith/UNI3DQHO3NRRJFSEFBYIE2CRXZ","download_json":"https://pith.science/pith/UNI3DQHO3NRRJFSEFBYIE2CRXZ.json","view_paper":"https://pith.science/paper/UNI3DQHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02588&json=true","fetch_graph":"https://pith.science/api/pith-number/UNI3DQHO3NRRJFSEFBYIE2CRXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/UNI3DQHO3NRRJFSEFBYIE2CRXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNI3DQHO3NRRJFSEFBYIE2CRXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNI3DQHO3NRRJFSEFBYIE2CRXZ/action/storage_attestation","attest_author":"https://pith.science/pith/UNI3DQHO3NRRJFSEFBYIE2CRXZ/action/author_attestation","sign_citation":"https://pith.science/pith/UNI3DQHO3NRRJFSEFBYIE2CRXZ/action/citation_signature","submit_replication":"https://pith.science/pith/UNI3DQHO3NRRJFSEFBYIE2CRXZ/action/replication_record"}},"created_at":"2026-07-05T08:03:58.660337+00:00","updated_at":"2026-07-05T08:03:58.660337+00:00"}