{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AXYYWSYN3ZBNN6ZB23SQWIA2NN","short_pith_number":"pith:AXYYWSYN","schema_version":"1.0","canonical_sha256":"05f18b4b0dde42d6fb21d6e50b201a6b4b025ed4103bbfeedbd0152b83595fd9","source":{"kind":"arxiv","id":"2107.04512","version":1},"attestation_state":"computed","paper":{"title":"Using Machine Translation to Localize Task Oriented NLG Output","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chris Varano, Cliff Brunk, Gagan Bansal, Justin Zhao, Kyu-Young Kim, Markus Freitag, Mihir Kale, Scott Roy, Sidharth Mudgal","submitted_at":"2021-07-09T15:56:45Z","abstract_excerpt":"One of the challenges in a task oriented natural language application like the Google Assistant, Siri, or Alexa is to localize the output to many languages. This paper explores doing this by applying machine translation to the English output. Using machine translation is very scalable, as it can work with any English output and can handle dynamic text, but otherwise the problem is a poor fit. The required quality bar is close to perfection, the range of sentences is extremely narrow, and the sentences are often very different than the ones in the machine translation training data. This combina"},"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":"2107.04512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-09T15:56:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"062f4f26447f5a1741b7336212cb5727dbcbea2c7a32e5e4f783ede5d57657ef","abstract_canon_sha256":"3bf20ca847f081491da750ce2ca8d80dfbf8dabb3d669210d0f829112b5d7adc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:34.105225Z","signature_b64":"dJ8j6tLyZhJYRgeNbXqlYqfnoNtIAC6sHo7+rVJ3E3AE+kad/4F68N31T/B1Nhp+BDscwjYDDOSeNTSwccJ+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05f18b4b0dde42d6fb21d6e50b201a6b4b025ed4103bbfeedbd0152b83595fd9","last_reissued_at":"2026-07-05T02:56:34.104778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:34.104778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Machine Translation to Localize Task Oriented NLG Output","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chris Varano, Cliff Brunk, Gagan Bansal, Justin Zhao, Kyu-Young Kim, Markus Freitag, Mihir Kale, Scott Roy, Sidharth Mudgal","submitted_at":"2021-07-09T15:56:45Z","abstract_excerpt":"One of the challenges in a task oriented natural language application like the Google Assistant, Siri, or Alexa is to localize the output to many languages. This paper explores doing this by applying machine translation to the English output. Using machine translation is very scalable, as it can work with any English output and can handle dynamic text, but otherwise the problem is a poor fit. The required quality bar is close to perfection, the range of sentences is extremely narrow, and the sentences are often very different than the ones in the machine translation training data. This combina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04512","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/2107.04512/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":"2107.04512","created_at":"2026-07-05T02:56:34.104835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.04512v1","created_at":"2026-07-05T02:56:34.104835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04512","created_at":"2026-07-05T02:56:34.104835+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXYYWSYN3ZBN","created_at":"2026-07-05T02:56:34.104835+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXYYWSYN3ZBNN6ZB","created_at":"2026-07-05T02:56:34.104835+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXYYWSYN","created_at":"2026-07-05T02:56:34.104835+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/AXYYWSYN3ZBNN6ZB23SQWIA2NN","json":"https://pith.science/pith/AXYYWSYN3ZBNN6ZB23SQWIA2NN.json","graph_json":"https://pith.science/api/pith-number/AXYYWSYN3ZBNN6ZB23SQWIA2NN/graph.json","events_json":"https://pith.science/api/pith-number/AXYYWSYN3ZBNN6ZB23SQWIA2NN/events.json","paper":"https://pith.science/paper/AXYYWSYN"},"agent_actions":{"view_html":"https://pith.science/pith/AXYYWSYN3ZBNN6ZB23SQWIA2NN","download_json":"https://pith.science/pith/AXYYWSYN3ZBNN6ZB23SQWIA2NN.json","view_paper":"https://pith.science/paper/AXYYWSYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.04512&json=true","fetch_graph":"https://pith.science/api/pith-number/AXYYWSYN3ZBNN6ZB23SQWIA2NN/graph.json","fetch_events":"https://pith.science/api/pith-number/AXYYWSYN3ZBNN6ZB23SQWIA2NN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXYYWSYN3ZBNN6ZB23SQWIA2NN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXYYWSYN3ZBNN6ZB23SQWIA2NN/action/storage_attestation","attest_author":"https://pith.science/pith/AXYYWSYN3ZBNN6ZB23SQWIA2NN/action/author_attestation","sign_citation":"https://pith.science/pith/AXYYWSYN3ZBNN6ZB23SQWIA2NN/action/citation_signature","submit_replication":"https://pith.science/pith/AXYYWSYN3ZBNN6ZB23SQWIA2NN/action/replication_record"}},"created_at":"2026-07-05T02:56:34.104835+00:00","updated_at":"2026-07-05T02:56:34.104835+00:00"}