{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:747QUN3WAIOBNT4FDBTDJQUTJ3","short_pith_number":"pith:747QUN3W","schema_version":"1.0","canonical_sha256":"ff3f0a3776021c16cf85186634c2934ee83ce67ef9402d804b0fb9e56a6410e3","source":{"kind":"arxiv","id":"1812.06876","version":2},"attestation_state":"computed","paper":{"title":"Multi-task learning to improve natural language understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Waibel, Jan Niehues, Stefan Constantin","submitted_at":"2018-12-17T16:32:05Z","abstract_excerpt":"Recently advancements in sequence-to-sequence neural network architectures have led to an improved natural language understanding. When building a neural network-based Natural Language Understanding component, one main challenge is to collect enough training data. The generation of a synthetic dataset is an inexpensive and quick way to collect data. Since this data often has less variety than real natural language, neural networks often have problems to generalize to unseen utterances during testing. In this work, we address this challenge by using multi-task learning. We train out-of-domain r"},"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":"1812.06876","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-17T16:32:05Z","cross_cats_sorted":[],"title_canon_sha256":"a20f83a225797f1dac3d2c715af11a43c6134e144552602c3962f0d417f661ba","abstract_canon_sha256":"201287b249848881b314ee092e16cd0083dc4044c9fb12867d693b62bc8f0742"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:55.525546Z","signature_b64":"x6FeHwf7UFM8382MsJ+9Sok65MzIvVJwyl+rwPnlsXVgqywi/6HGr5KY40fqoiFTo4+jxXCSUAN0rXAvS7tdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff3f0a3776021c16cf85186634c2934ee83ce67ef9402d804b0fb9e56a6410e3","last_reissued_at":"2026-05-17T23:53:55.524831Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:55.524831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-task learning to improve natural language understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Waibel, Jan Niehues, Stefan Constantin","submitted_at":"2018-12-17T16:32:05Z","abstract_excerpt":"Recently advancements in sequence-to-sequence neural network architectures have led to an improved natural language understanding. When building a neural network-based Natural Language Understanding component, one main challenge is to collect enough training data. The generation of a synthetic dataset is an inexpensive and quick way to collect data. Since this data often has less variety than real natural language, neural networks often have problems to generalize to unseen utterances during testing. In this work, we address this challenge by using multi-task learning. We train out-of-domain r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.06876","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":""},"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":"1812.06876","created_at":"2026-05-17T23:53:55.524950+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.06876v2","created_at":"2026-05-17T23:53:55.524950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.06876","created_at":"2026-05-17T23:53:55.524950+00:00"},{"alias_kind":"pith_short_12","alias_value":"747QUN3WAIOB","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"747QUN3WAIOBNT4F","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"747QUN3W","created_at":"2026-05-18T12:32:11.075285+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/747QUN3WAIOBNT4FDBTDJQUTJ3","json":"https://pith.science/pith/747QUN3WAIOBNT4FDBTDJQUTJ3.json","graph_json":"https://pith.science/api/pith-number/747QUN3WAIOBNT4FDBTDJQUTJ3/graph.json","events_json":"https://pith.science/api/pith-number/747QUN3WAIOBNT4FDBTDJQUTJ3/events.json","paper":"https://pith.science/paper/747QUN3W"},"agent_actions":{"view_html":"https://pith.science/pith/747QUN3WAIOBNT4FDBTDJQUTJ3","download_json":"https://pith.science/pith/747QUN3WAIOBNT4FDBTDJQUTJ3.json","view_paper":"https://pith.science/paper/747QUN3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.06876&json=true","fetch_graph":"https://pith.science/api/pith-number/747QUN3WAIOBNT4FDBTDJQUTJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/747QUN3WAIOBNT4FDBTDJQUTJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/747QUN3WAIOBNT4FDBTDJQUTJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/747QUN3WAIOBNT4FDBTDJQUTJ3/action/storage_attestation","attest_author":"https://pith.science/pith/747QUN3WAIOBNT4FDBTDJQUTJ3/action/author_attestation","sign_citation":"https://pith.science/pith/747QUN3WAIOBNT4FDBTDJQUTJ3/action/citation_signature","submit_replication":"https://pith.science/pith/747QUN3WAIOBNT4FDBTDJQUTJ3/action/replication_record"}},"created_at":"2026-05-17T23:53:55.524950+00:00","updated_at":"2026-05-17T23:53:55.524950+00:00"}