{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4CNH3TVULZJ56TVKPFVRTSMSCV","short_pith_number":"pith:4CNH3TVU","schema_version":"1.0","canonical_sha256":"e09a7dceb45e53df4eaa796b19c9921576a26f73b5b45b217e297975ab408b90","source":{"kind":"arxiv","id":"2011.02821","version":3},"attestation_state":"computed","paper":{"title":"Data Augmentation and Terminology Integration for Domain-Specific Sinhala-English-Tamil Statistical Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aloka Fernando, Gihan Dias, Surangika Ranathunga","submitted_at":"2020-11-05T13:58:32Z","abstract_excerpt":"Out of vocabulary (OOV) is a problem in the context of Machine Translation (MT) in low-resourced languages. When source and/or target languages are morphologically rich, it becomes even worse. Bilingual list integration is an approach to address the OOV problem. This allows more words to be translated than are in the training data. However, since bilingual lists contain words in the base form, it will not translate inflected forms for morphologically rich languages such as Sinhala and Tamil. This paper focuses on data augmentation techniques where bilingual lexicon terms are expanded based on "},"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":"2011.02821","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-05T13:58:32Z","cross_cats_sorted":[],"title_canon_sha256":"2d44a78339b032e8b44120713a1fa73c64364211f6dea4bfb2b89e00916d18e2","abstract_canon_sha256":"21322f838522e7b8cfa4759295586a59867d2d7844af81485fdc1b4561b8470e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:12:31.312169Z","signature_b64":"RYPSbD5ihBEuFSs8jHyWuQwl7rVK+1lG3Kmfz6FacQZi9LGG7UUPn4ccftVP2NlYVfyKZAGgRG1OxtTEDrHdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e09a7dceb45e53df4eaa796b19c9921576a26f73b5b45b217e297975ab408b90","last_reissued_at":"2026-07-05T02:12:31.311823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:12:31.311823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Augmentation and Terminology Integration for Domain-Specific Sinhala-English-Tamil Statistical Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aloka Fernando, Gihan Dias, Surangika Ranathunga","submitted_at":"2020-11-05T13:58:32Z","abstract_excerpt":"Out of vocabulary (OOV) is a problem in the context of Machine Translation (MT) in low-resourced languages. When source and/or target languages are morphologically rich, it becomes even worse. Bilingual list integration is an approach to address the OOV problem. This allows more words to be translated than are in the training data. However, since bilingual lists contain words in the base form, it will not translate inflected forms for morphologically rich languages such as Sinhala and Tamil. This paper focuses on data augmentation techniques where bilingual lexicon terms are expanded based on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02821","kind":"arxiv","version":3},"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/2011.02821/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":"2011.02821","created_at":"2026-07-05T02:12:31.311878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.02821v3","created_at":"2026-07-05T02:12:31.311878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02821","created_at":"2026-07-05T02:12:31.311878+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CNH3TVULZJ5","created_at":"2026-07-05T02:12:31.311878+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CNH3TVULZJ56TVK","created_at":"2026-07-05T02:12:31.311878+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CNH3TVU","created_at":"2026-07-05T02:12:31.311878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16894","citing_title":"Unsupervised Bilingual Lexicon Induction for Low Resource Languages","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4CNH3TVULZJ56TVKPFVRTSMSCV","json":"https://pith.science/pith/4CNH3TVULZJ56TVKPFVRTSMSCV.json","graph_json":"https://pith.science/api/pith-number/4CNH3TVULZJ56TVKPFVRTSMSCV/graph.json","events_json":"https://pith.science/api/pith-number/4CNH3TVULZJ56TVKPFVRTSMSCV/events.json","paper":"https://pith.science/paper/4CNH3TVU"},"agent_actions":{"view_html":"https://pith.science/pith/4CNH3TVULZJ56TVKPFVRTSMSCV","download_json":"https://pith.science/pith/4CNH3TVULZJ56TVKPFVRTSMSCV.json","view_paper":"https://pith.science/paper/4CNH3TVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.02821&json=true","fetch_graph":"https://pith.science/api/pith-number/4CNH3TVULZJ56TVKPFVRTSMSCV/graph.json","fetch_events":"https://pith.science/api/pith-number/4CNH3TVULZJ56TVKPFVRTSMSCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CNH3TVULZJ56TVKPFVRTSMSCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CNH3TVULZJ56TVKPFVRTSMSCV/action/storage_attestation","attest_author":"https://pith.science/pith/4CNH3TVULZJ56TVKPFVRTSMSCV/action/author_attestation","sign_citation":"https://pith.science/pith/4CNH3TVULZJ56TVKPFVRTSMSCV/action/citation_signature","submit_replication":"https://pith.science/pith/4CNH3TVULZJ56TVKPFVRTSMSCV/action/replication_record"}},"created_at":"2026-07-05T02:12:31.311878+00:00","updated_at":"2026-07-05T02:12:31.311878+00:00"}