{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GXQODCBQ33H7BPRZZ7OCQAPX5R","short_pith_number":"pith:GXQODCBQ","schema_version":"1.0","canonical_sha256":"35e0e18830decff0be39cfdc2801f7ec5f039b0afa8854312bca11104e0ccbad","source":{"kind":"arxiv","id":"2210.10692","version":2},"attestation_state":"computed","paper":{"title":"Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Emezue, Everlyn Asiko, Idris Abdulmumin, Jesujoba O. Alabi, Michael Beukman, Mofetoluwa Adeyemi, Oreen Yousuf, Sahib Singh, Shamsuddeen Hassan Muhammad, Tajuddeen Rabiu Gwadabe, Tosin Adewumi","submitted_at":"2022-10-19T16:12:27Z","abstract_excerpt":"We participated in the WMT 2022 Large-Scale Machine Translation Evaluation for the African Languages Shared Task. This work describes our approach, which is based on filtering the given noisy data using a sentence-pair classifier that was built by fine-tuning a pre-trained language model. To train the classifier, we obtain positive samples (i.e. high-quality parallel sentences) from a gold-standard curated dataset and extract negative samples (i.e. low-quality parallel sentences) from automatically aligned parallel data by choosing sentences with low alignment scores. Our final machine transla"},"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":"2210.10692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-19T16:12:27Z","cross_cats_sorted":[],"title_canon_sha256":"ef28d1e7b8f415adeed2bef071d5fae430beb6bf33646eaa472011ce9a942526","abstract_canon_sha256":"6f689eddf706c502f3974c22d920371e82ae6cc2381e3b32fd42a33bffd07eb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:31.958828Z","signature_b64":"0qq/rtYxyiTYio5a3fbFjuzQGc/5lnEgZaQabG9C/4EIKJWdqgF3fghJXoqCOp4Qr7sP0zV+ENYTydLZtvZ+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35e0e18830decff0be39cfdc2801f7ec5f039b0afa8854312bca11104e0ccbad","last_reissued_at":"2026-07-05T05:08:31.958486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:31.958486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Emezue, Everlyn Asiko, Idris Abdulmumin, Jesujoba O. Alabi, Michael Beukman, Mofetoluwa Adeyemi, Oreen Yousuf, Sahib Singh, Shamsuddeen Hassan Muhammad, Tajuddeen Rabiu Gwadabe, Tosin Adewumi","submitted_at":"2022-10-19T16:12:27Z","abstract_excerpt":"We participated in the WMT 2022 Large-Scale Machine Translation Evaluation for the African Languages Shared Task. This work describes our approach, which is based on filtering the given noisy data using a sentence-pair classifier that was built by fine-tuning a pre-trained language model. To train the classifier, we obtain positive samples (i.e. high-quality parallel sentences) from a gold-standard curated dataset and extract negative samples (i.e. low-quality parallel sentences) from automatically aligned parallel data by choosing sentences with low alignment scores. Our final machine transla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10692","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.10692/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":"2210.10692","created_at":"2026-07-05T05:08:31.958547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.10692v2","created_at":"2026-07-05T05:08:31.958547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10692","created_at":"2026-07-05T05:08:31.958547+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXQODCBQ33H7","created_at":"2026-07-05T05:08:31.958547+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXQODCBQ33H7BPRZ","created_at":"2026-07-05T05:08:31.958547+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXQODCBQ","created_at":"2026-07-05T05:08:31.958547+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/GXQODCBQ33H7BPRZZ7OCQAPX5R","json":"https://pith.science/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R.json","graph_json":"https://pith.science/api/pith-number/GXQODCBQ33H7BPRZZ7OCQAPX5R/graph.json","events_json":"https://pith.science/api/pith-number/GXQODCBQ33H7BPRZZ7OCQAPX5R/events.json","paper":"https://pith.science/paper/GXQODCBQ"},"agent_actions":{"view_html":"https://pith.science/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R","download_json":"https://pith.science/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R.json","view_paper":"https://pith.science/paper/GXQODCBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.10692&json=true","fetch_graph":"https://pith.science/api/pith-number/GXQODCBQ33H7BPRZZ7OCQAPX5R/graph.json","fetch_events":"https://pith.science/api/pith-number/GXQODCBQ33H7BPRZZ7OCQAPX5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R/action/storage_attestation","attest_author":"https://pith.science/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R/action/author_attestation","sign_citation":"https://pith.science/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R/action/citation_signature","submit_replication":"https://pith.science/pith/GXQODCBQ33H7BPRZZ7OCQAPX5R/action/replication_record"}},"created_at":"2026-07-05T05:08:31.958547+00:00","updated_at":"2026-07-05T05:08:31.958547+00:00"}