{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MSP5ZRFP2TMJG5TAERJFRSBZQ5","short_pith_number":"pith:MSP5ZRFP","schema_version":"1.0","canonical_sha256":"649fdcc4afd4d8937660245258c8398755dfed7869ba9029e1cddcfb01fe78f1","source":{"kind":"arxiv","id":"2109.06262","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Multiway Multilingual NMT in the Turkic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahsan Wahab, Aigiz Kunafin, Anoop Babu, Behzod Moydinboyev, Duygu Ataman, Francis Tyers, Jamshidbek Mirzakhalov, John Licato, Julia Kreutzer, Mokhiyakhon Uzokova, Orhan Firat, Sardana Ivanova, Shaxnoza Pulatova, Sriram Chellappan","submitted_at":"2021-09-13T19:01:07Z","abstract_excerpt":"Despite the increasing number of large and comprehensive machine translation (MT) systems, evaluation of these methods in various languages has been restrained by the lack of high-quality parallel corpora as well as engagement with the people that speak these languages. In this study, we present an evaluation of state-of-the-art approaches to training and evaluating MT systems in 22 languages from the Turkic language family, most of which being extremely under-explored. First, we adopt the TIL Corpus with a few key improvements to the training and the evaluation sets. Then, we train 26 bilingu"},"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":"2109.06262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T19:01:07Z","cross_cats_sorted":[],"title_canon_sha256":"b698064118d97e5599fd123208238da0d72f56d7269c5b8c4522f8e1256e768f","abstract_canon_sha256":"09fa768ad4b18f2b83d6ae06c5ed1fb49019483f39caac9318151afb374a1530"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:52.377913Z","signature_b64":"hzm/WOJjd9NsU8NCteOWj8vCeE9u2TanmtFYBGz8lgLPjj2hwh6SENijqWRSz6NJu7P7HyexO5AA2X2t63ICBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"649fdcc4afd4d8937660245258c8398755dfed7869ba9029e1cddcfb01fe78f1","last_reissued_at":"2026-07-05T03:13:52.377381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:52.377381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Multiway Multilingual NMT in the Turkic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahsan Wahab, Aigiz Kunafin, Anoop Babu, Behzod Moydinboyev, Duygu Ataman, Francis Tyers, Jamshidbek Mirzakhalov, John Licato, Julia Kreutzer, Mokhiyakhon Uzokova, Orhan Firat, Sardana Ivanova, Shaxnoza Pulatova, Sriram Chellappan","submitted_at":"2021-09-13T19:01:07Z","abstract_excerpt":"Despite the increasing number of large and comprehensive machine translation (MT) systems, evaluation of these methods in various languages has been restrained by the lack of high-quality parallel corpora as well as engagement with the people that speak these languages. In this study, we present an evaluation of state-of-the-art approaches to training and evaluating MT systems in 22 languages from the Turkic language family, most of which being extremely under-explored. First, we adopt the TIL Corpus with a few key improvements to the training and the evaluation sets. Then, we train 26 bilingu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06262","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/2109.06262/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":"2109.06262","created_at":"2026-07-05T03:13:52.377442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.06262v1","created_at":"2026-07-05T03:13:52.377442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06262","created_at":"2026-07-05T03:13:52.377442+00:00"},{"alias_kind":"pith_short_12","alias_value":"MSP5ZRFP2TMJ","created_at":"2026-07-05T03:13:52.377442+00:00"},{"alias_kind":"pith_short_16","alias_value":"MSP5ZRFP2TMJG5TA","created_at":"2026-07-05T03:13:52.377442+00:00"},{"alias_kind":"pith_short_8","alias_value":"MSP5ZRFP","created_at":"2026-07-05T03:13:52.377442+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/MSP5ZRFP2TMJG5TAERJFRSBZQ5","json":"https://pith.science/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5.json","graph_json":"https://pith.science/api/pith-number/MSP5ZRFP2TMJG5TAERJFRSBZQ5/graph.json","events_json":"https://pith.science/api/pith-number/MSP5ZRFP2TMJG5TAERJFRSBZQ5/events.json","paper":"https://pith.science/paper/MSP5ZRFP"},"agent_actions":{"view_html":"https://pith.science/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5","download_json":"https://pith.science/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5.json","view_paper":"https://pith.science/paper/MSP5ZRFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.06262&json=true","fetch_graph":"https://pith.science/api/pith-number/MSP5ZRFP2TMJG5TAERJFRSBZQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/MSP5ZRFP2TMJG5TAERJFRSBZQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5/action/storage_attestation","attest_author":"https://pith.science/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5/action/author_attestation","sign_citation":"https://pith.science/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5/action/citation_signature","submit_replication":"https://pith.science/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5/action/replication_record"}},"created_at":"2026-07-05T03:13:52.377442+00:00","updated_at":"2026-07-05T03:13:52.377442+00:00"}