{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3ARCV55MUOV66YYCWFBN7Z3YDS","short_pith_number":"pith:3ARCV55M","schema_version":"1.0","canonical_sha256":"d8222af7aca3abef6302b142dfe7781c845670032ff83111be0a8a2cb1b244a0","source":{"kind":"arxiv","id":"2103.11189","version":1},"attestation_state":"computed","paper":{"title":"The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Constantine Lignos, Jonne S\\\"alev\\\"a","submitted_at":"2021-03-20T14:39:25Z","abstract_excerpt":"This paper evaluates the performance of several modern subword segmentation methods in a low-resource neural machine translation setting. We compare segmentations produced by applying BPE at the token or sentence level with morphologically-based segmentations from LMVR and MORSEL. We evaluate translation tasks between English and each of Nepali, Sinhala, and Kazakh, and predict that using morphologically-based segmentation methods would lead to better performance in this setting. However, comparing to BPE, we find that no consistent and reliable differences emerge between the segmentation meth"},"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":"2103.11189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-20T14:39:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eb78d7daab94a8b23780058026c3610c0ba01b3a03f7076fa31e407f6d5a071d","abstract_canon_sha256":"1ca841bb14b99410ac03dd6ba5138925f2bedcb3ea088690f4e12598d58dc89b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:32.298482Z","signature_b64":"fsbRDsPKNqJsRY09EaG1I094mrDEJWiLbqmQL1xtSNSkksC4vX38yfEs0XqJJwt+OqaZHk2rMjuGjJGvx8dZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8222af7aca3abef6302b142dfe7781c845670032ff83111be0a8a2cb1b244a0","last_reissued_at":"2026-07-05T08:19:32.297946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:32.297946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Constantine Lignos, Jonne S\\\"alev\\\"a","submitted_at":"2021-03-20T14:39:25Z","abstract_excerpt":"This paper evaluates the performance of several modern subword segmentation methods in a low-resource neural machine translation setting. We compare segmentations produced by applying BPE at the token or sentence level with morphologically-based segmentations from LMVR and MORSEL. We evaluate translation tasks between English and each of Nepali, Sinhala, and Kazakh, and predict that using morphologically-based segmentation methods would lead to better performance in this setting. However, comparing to BPE, we find that no consistent and reliable differences emerge between the segmentation meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11189","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/2103.11189/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":"2103.11189","created_at":"2026-07-05T08:19:32.298008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.11189v1","created_at":"2026-07-05T08:19:32.298008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11189","created_at":"2026-07-05T08:19:32.298008+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ARCV55MUOV6","created_at":"2026-07-05T08:19:32.298008+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ARCV55MUOV66YYC","created_at":"2026-07-05T08:19:32.298008+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ARCV55M","created_at":"2026-07-05T08:19:32.298008+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/3ARCV55MUOV66YYCWFBN7Z3YDS","json":"https://pith.science/pith/3ARCV55MUOV66YYCWFBN7Z3YDS.json","graph_json":"https://pith.science/api/pith-number/3ARCV55MUOV66YYCWFBN7Z3YDS/graph.json","events_json":"https://pith.science/api/pith-number/3ARCV55MUOV66YYCWFBN7Z3YDS/events.json","paper":"https://pith.science/paper/3ARCV55M"},"agent_actions":{"view_html":"https://pith.science/pith/3ARCV55MUOV66YYCWFBN7Z3YDS","download_json":"https://pith.science/pith/3ARCV55MUOV66YYCWFBN7Z3YDS.json","view_paper":"https://pith.science/paper/3ARCV55M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.11189&json=true","fetch_graph":"https://pith.science/api/pith-number/3ARCV55MUOV66YYCWFBN7Z3YDS/graph.json","fetch_events":"https://pith.science/api/pith-number/3ARCV55MUOV66YYCWFBN7Z3YDS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ARCV55MUOV66YYCWFBN7Z3YDS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ARCV55MUOV66YYCWFBN7Z3YDS/action/storage_attestation","attest_author":"https://pith.science/pith/3ARCV55MUOV66YYCWFBN7Z3YDS/action/author_attestation","sign_citation":"https://pith.science/pith/3ARCV55MUOV66YYCWFBN7Z3YDS/action/citation_signature","submit_replication":"https://pith.science/pith/3ARCV55MUOV66YYCWFBN7Z3YDS/action/replication_record"}},"created_at":"2026-07-05T08:19:32.298008+00:00","updated_at":"2026-07-05T08:19:32.298008+00:00"}