{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:G75I6UX5TVFCQFRTNYL2MPUPBE","short_pith_number":"pith:G75I6UX5","schema_version":"1.0","canonical_sha256":"37fa8f52fd9d4a2816336e17a63e8f091dfbd35bc3cd6a87eda777e6b4eab3f8","source":{"kind":"arxiv","id":"1805.09119","version":1},"attestation_state":"computed","paper":{"title":"Selecting Machine-Translated Data for Quick Bootstrapping of a Natural Language Understanding System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Judith Gaspers, Penny Karanasou, Rajen Chatterjee","submitted_at":"2018-05-23T13:20:16Z","abstract_excerpt":"This paper investigates the use of Machine Translation (MT) to bootstrap a Natural Language Understanding (NLU) system for a new language for the use case of a large-scale voice-controlled device. The goal is to decrease the cost and time needed to get an annotated corpus for the new language, while still having a large enough coverage of user requests. Different methods of filtering MT data in order to keep utterances that improve NLU performance and language-specific post-processing methods are investigated. These methods are tested in a large-scale NLU task with translating around 10 millio"},"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":"1805.09119","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-23T13:20:16Z","cross_cats_sorted":[],"title_canon_sha256":"e7a44f38ff575138f16ada1431717d49fdb8b895eed8bbf9319c8102dde470e1","abstract_canon_sha256":"2cbdbfd61e41ddc69c232ca3be1d72320e39f9dfa5de525c4915d37cf9aadeb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:08.526743Z","signature_b64":"XADWjFgGQiX+6qCavDtYObt1qy71nKylCexQ23+fVi1ZgrXc2JQi9ywgtOcLyg9Ts2BjuX1WCNOyOhrebrU2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37fa8f52fd9d4a2816336e17a63e8f091dfbd35bc3cd6a87eda777e6b4eab3f8","last_reissued_at":"2026-05-18T00:15:08.526338Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:08.526338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Selecting Machine-Translated Data for Quick Bootstrapping of a Natural Language Understanding System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Judith Gaspers, Penny Karanasou, Rajen Chatterjee","submitted_at":"2018-05-23T13:20:16Z","abstract_excerpt":"This paper investigates the use of Machine Translation (MT) to bootstrap a Natural Language Understanding (NLU) system for a new language for the use case of a large-scale voice-controlled device. The goal is to decrease the cost and time needed to get an annotated corpus for the new language, while still having a large enough coverage of user requests. Different methods of filtering MT data in order to keep utterances that improve NLU performance and language-specific post-processing methods are investigated. These methods are tested in a large-scale NLU task with translating around 10 millio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09119","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":""},"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":"1805.09119","created_at":"2026-05-18T00:15:08.526401+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09119v1","created_at":"2026-05-18T00:15:08.526401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09119","created_at":"2026-05-18T00:15:08.526401+00:00"},{"alias_kind":"pith_short_12","alias_value":"G75I6UX5TVFC","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"G75I6UX5TVFCQFRT","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"G75I6UX5","created_at":"2026-05-18T12:32:25.280505+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/G75I6UX5TVFCQFRTNYL2MPUPBE","json":"https://pith.science/pith/G75I6UX5TVFCQFRTNYL2MPUPBE.json","graph_json":"https://pith.science/api/pith-number/G75I6UX5TVFCQFRTNYL2MPUPBE/graph.json","events_json":"https://pith.science/api/pith-number/G75I6UX5TVFCQFRTNYL2MPUPBE/events.json","paper":"https://pith.science/paper/G75I6UX5"},"agent_actions":{"view_html":"https://pith.science/pith/G75I6UX5TVFCQFRTNYL2MPUPBE","download_json":"https://pith.science/pith/G75I6UX5TVFCQFRTNYL2MPUPBE.json","view_paper":"https://pith.science/paper/G75I6UX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09119&json=true","fetch_graph":"https://pith.science/api/pith-number/G75I6UX5TVFCQFRTNYL2MPUPBE/graph.json","fetch_events":"https://pith.science/api/pith-number/G75I6UX5TVFCQFRTNYL2MPUPBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G75I6UX5TVFCQFRTNYL2MPUPBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G75I6UX5TVFCQFRTNYL2MPUPBE/action/storage_attestation","attest_author":"https://pith.science/pith/G75I6UX5TVFCQFRTNYL2MPUPBE/action/author_attestation","sign_citation":"https://pith.science/pith/G75I6UX5TVFCQFRTNYL2MPUPBE/action/citation_signature","submit_replication":"https://pith.science/pith/G75I6UX5TVFCQFRTNYL2MPUPBE/action/replication_record"}},"created_at":"2026-05-18T00:15:08.526401+00:00","updated_at":"2026-05-18T00:15:08.526401+00:00"}