{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JQSBO7LTLK5VD2BNWFOWS7V65V","short_pith_number":"pith:JQSBO7LT","schema_version":"1.0","canonical_sha256":"4c24177d735abb51e82db15d697ebeed78b5ae30de292b5fa34679d994e995a3","source":{"kind":"arxiv","id":"2403.08189","version":1},"attestation_state":"computed","paper":{"title":"Embedded Translations for Low-resource Automated Glossing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changbing Yang, Garrett Nicolai, Miikka Silfverberg","submitted_at":"2024-03-13T02:23:13Z","abstract_excerpt":"We investigate automatic interlinear glossing in low-resource settings. We augment a hard-attentional neural model with embedded translation information extracted from interlinear glossed text. After encoding these translations using large language models, specifically BERT and T5, we introduce a character-level decoder for generating glossed output. Aided by these enhancements, our model demonstrates an average improvement of 3.97\\%-points over the previous state of the art on datasets from the SIGMORPHON 2023 Shared Task on Interlinear Glossing. In a simulated ultra low-resource setting, tra"},"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":"2403.08189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T02:23:13Z","cross_cats_sorted":[],"title_canon_sha256":"227875a8af2379f6787ca7692a59f7fb0bea204f114d6ab0adcc058795bc6b98","abstract_canon_sha256":"656c03773db6bafc340f738f7f565c44c846693368c67ff79cd5a2d48e47ebf4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:35.349004Z","signature_b64":"C/RJi1hrnNOAU06PXwXF8OAssHNCsNzYw3ywiSp8/U/iEhSxii5JjlFNodg913B68V6OyfZQCBEYd43kTLUvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c24177d735abb51e82db15d697ebeed78b5ae30de292b5fa34679d994e995a3","last_reissued_at":"2026-07-05T07:55:35.348501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:35.348501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embedded Translations for Low-resource Automated Glossing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changbing Yang, Garrett Nicolai, Miikka Silfverberg","submitted_at":"2024-03-13T02:23:13Z","abstract_excerpt":"We investigate automatic interlinear glossing in low-resource settings. We augment a hard-attentional neural model with embedded translation information extracted from interlinear glossed text. After encoding these translations using large language models, specifically BERT and T5, we introduce a character-level decoder for generating glossed output. Aided by these enhancements, our model demonstrates an average improvement of 3.97\\%-points over the previous state of the art on datasets from the SIGMORPHON 2023 Shared Task on Interlinear Glossing. In a simulated ultra low-resource setting, tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08189","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/2403.08189/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":"2403.08189","created_at":"2026-07-05T07:55:35.348572+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08189v1","created_at":"2026-07-05T07:55:35.348572+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08189","created_at":"2026-07-05T07:55:35.348572+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQSBO7LTLK5V","created_at":"2026-07-05T07:55:35.348572+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQSBO7LTLK5VD2BN","created_at":"2026-07-05T07:55:35.348572+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQSBO7LT","created_at":"2026-07-05T07:55:35.348572+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/JQSBO7LTLK5VD2BNWFOWS7V65V","json":"https://pith.science/pith/JQSBO7LTLK5VD2BNWFOWS7V65V.json","graph_json":"https://pith.science/api/pith-number/JQSBO7LTLK5VD2BNWFOWS7V65V/graph.json","events_json":"https://pith.science/api/pith-number/JQSBO7LTLK5VD2BNWFOWS7V65V/events.json","paper":"https://pith.science/paper/JQSBO7LT"},"agent_actions":{"view_html":"https://pith.science/pith/JQSBO7LTLK5VD2BNWFOWS7V65V","download_json":"https://pith.science/pith/JQSBO7LTLK5VD2BNWFOWS7V65V.json","view_paper":"https://pith.science/paper/JQSBO7LT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08189&json=true","fetch_graph":"https://pith.science/api/pith-number/JQSBO7LTLK5VD2BNWFOWS7V65V/graph.json","fetch_events":"https://pith.science/api/pith-number/JQSBO7LTLK5VD2BNWFOWS7V65V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQSBO7LTLK5VD2BNWFOWS7V65V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQSBO7LTLK5VD2BNWFOWS7V65V/action/storage_attestation","attest_author":"https://pith.science/pith/JQSBO7LTLK5VD2BNWFOWS7V65V/action/author_attestation","sign_citation":"https://pith.science/pith/JQSBO7LTLK5VD2BNWFOWS7V65V/action/citation_signature","submit_replication":"https://pith.science/pith/JQSBO7LTLK5VD2BNWFOWS7V65V/action/replication_record"}},"created_at":"2026-07-05T07:55:35.348572+00:00","updated_at":"2026-07-05T07:55:35.348572+00:00"}