{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2QKKRTX6LGY4DLXX2X7BUXMCNN","short_pith_number":"pith:2QKKRTX6","schema_version":"1.0","canonical_sha256":"d414a8cefe59b1c1aef7d5fe1a5d826b76d7596758a2e93fd7f504d430ace195","source":{"kind":"arxiv","id":"2105.07476","version":1},"attestation_state":"computed","paper":{"title":"Data Augmentation for Sign Language Gloss Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amit Moryossef, Graham Neubig, Kayo Yin, Yoav Goldberg","submitted_at":"2021-05-16T16:37:36Z","abstract_excerpt":"Sign language translation (SLT) is often decomposed into video-to-gloss recognition and gloss-to-text translation, where a gloss is a sequence of transcribed spoken-language words in the order in which they are signed. We focus here on gloss-to-text translation, which we treat as a low-resource neural machine translation (NMT) problem. However, unlike traditional low-resource NMT, gloss-to-text translation differs because gloss-text pairs often have a higher lexical overlap and lower syntactic overlap than pairs of spoken languages. We exploit this lexical overlap and handle syntactic divergen"},"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":"2105.07476","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-16T16:37:36Z","cross_cats_sorted":[],"title_canon_sha256":"8d91a5a2d85956c824ee699760b867d8f01e4c8a905aac9ab5bc9e3e074050f6","abstract_canon_sha256":"22c3b765ffea81c047ab4d8a28d8d931db9f2e21731a5b33d3add66847583064"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:41.099625Z","signature_b64":"SfjQ0zd3Cts9nfCuJDzRH7nHAj8B3aY9rPwyIuznbkEomckwXqH6ZQEOK9eoO+aZa8FSMYl+ihsSMEZDyG/EDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d414a8cefe59b1c1aef7d5fe1a5d826b76d7596758a2e93fd7f504d430ace195","last_reissued_at":"2026-07-05T02:40:41.099259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:41.099259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Augmentation for Sign Language Gloss Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amit Moryossef, Graham Neubig, Kayo Yin, Yoav Goldberg","submitted_at":"2021-05-16T16:37:36Z","abstract_excerpt":"Sign language translation (SLT) is often decomposed into video-to-gloss recognition and gloss-to-text translation, where a gloss is a sequence of transcribed spoken-language words in the order in which they are signed. We focus here on gloss-to-text translation, which we treat as a low-resource neural machine translation (NMT) problem. However, unlike traditional low-resource NMT, gloss-to-text translation differs because gloss-text pairs often have a higher lexical overlap and lower syntactic overlap than pairs of spoken languages. We exploit this lexical overlap and handle syntactic divergen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.07476","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/2105.07476/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":"2105.07476","created_at":"2026-07-05T02:40:41.099322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.07476v1","created_at":"2026-07-05T02:40:41.099322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.07476","created_at":"2026-07-05T02:40:41.099322+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QKKRTX6LGY4","created_at":"2026-07-05T02:40:41.099322+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QKKRTX6LGY4DLXX","created_at":"2026-07-05T02:40:41.099322+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QKKRTX6","created_at":"2026-07-05T02:40:41.099322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09643","citing_title":"Using Sign Language Production as Data Augmentation to enhance Sign Language Translation","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2QKKRTX6LGY4DLXX2X7BUXMCNN","json":"https://pith.science/pith/2QKKRTX6LGY4DLXX2X7BUXMCNN.json","graph_json":"https://pith.science/api/pith-number/2QKKRTX6LGY4DLXX2X7BUXMCNN/graph.json","events_json":"https://pith.science/api/pith-number/2QKKRTX6LGY4DLXX2X7BUXMCNN/events.json","paper":"https://pith.science/paper/2QKKRTX6"},"agent_actions":{"view_html":"https://pith.science/pith/2QKKRTX6LGY4DLXX2X7BUXMCNN","download_json":"https://pith.science/pith/2QKKRTX6LGY4DLXX2X7BUXMCNN.json","view_paper":"https://pith.science/paper/2QKKRTX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.07476&json=true","fetch_graph":"https://pith.science/api/pith-number/2QKKRTX6LGY4DLXX2X7BUXMCNN/graph.json","fetch_events":"https://pith.science/api/pith-number/2QKKRTX6LGY4DLXX2X7BUXMCNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QKKRTX6LGY4DLXX2X7BUXMCNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QKKRTX6LGY4DLXX2X7BUXMCNN/action/storage_attestation","attest_author":"https://pith.science/pith/2QKKRTX6LGY4DLXX2X7BUXMCNN/action/author_attestation","sign_citation":"https://pith.science/pith/2QKKRTX6LGY4DLXX2X7BUXMCNN/action/citation_signature","submit_replication":"https://pith.science/pith/2QKKRTX6LGY4DLXX2X7BUXMCNN/action/replication_record"}},"created_at":"2026-07-05T02:40:41.099322+00:00","updated_at":"2026-07-05T02:40:41.099322+00:00"}