{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7LWN75W5YDYAFZNL6VPJYXMLZX","short_pith_number":"pith:7LWN75W5","schema_version":"1.0","canonical_sha256":"faecdff6ddc0f002e5abf55e9c5d8bcdd36dddc1622b5df5e3ea5fa0f8b53548","source":{"kind":"arxiv","id":"2401.05727","version":1},"attestation_state":"computed","paper":{"title":"Zero Resource Cross-Lingual Part Of Speech Tagging","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sahil Chopra","submitted_at":"2024-01-11T08:12:47Z","abstract_excerpt":"Part of speech tagging in zero-resource settings can be an effective approach for low-resource languages when no labeled training data is available. Existing systems use two main techniques for POS tagging i.e. pretrained multilingual large language models(LLM) or project the source language labels into the zero resource target language and train a sequence labeling model on it. We explore the latter approach using the off-the-shelf alignment module and train a hidden Markov model(HMM) to predict the POS tags. We evaluate transfer learning setup with English as a source language and French, Ge"},"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":"2401.05727","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T08:12:47Z","cross_cats_sorted":[],"title_canon_sha256":"b78450371c58a5e297b941712c0284a0a088f023fb57309d0870a3aa9c07a97e","abstract_canon_sha256":"e5d70906e93d7eaae168704647f6344fa47bd5b86536e24e50f230c2444fd3a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:34.562871Z","signature_b64":"3Twa0PNs7mcM6/AapzCPlTfRdbaIqEgI0sGHtVolS7CFZxAZrf8YewNvV26Qoyo8U2ZNugZFFCpbkmaLpLjuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"faecdff6ddc0f002e5abf55e9c5d8bcdd36dddc1622b5df5e3ea5fa0f8b53548","last_reissued_at":"2026-07-05T07:32:34.562396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:34.562396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero Resource Cross-Lingual Part Of Speech Tagging","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sahil Chopra","submitted_at":"2024-01-11T08:12:47Z","abstract_excerpt":"Part of speech tagging in zero-resource settings can be an effective approach for low-resource languages when no labeled training data is available. Existing systems use two main techniques for POS tagging i.e. pretrained multilingual large language models(LLM) or project the source language labels into the zero resource target language and train a sequence labeling model on it. We explore the latter approach using the off-the-shelf alignment module and train a hidden Markov model(HMM) to predict the POS tags. We evaluate transfer learning setup with English as a source language and French, Ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05727","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/2401.05727/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":"2401.05727","created_at":"2026-07-05T07:32:34.562456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.05727v1","created_at":"2026-07-05T07:32:34.562456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05727","created_at":"2026-07-05T07:32:34.562456+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LWN75W5YDYA","created_at":"2026-07-05T07:32:34.562456+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LWN75W5YDYAFZNL","created_at":"2026-07-05T07:32:34.562456+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LWN75W5","created_at":"2026-07-05T07:32:34.562456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17715","citing_title":"Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7LWN75W5YDYAFZNL6VPJYXMLZX","json":"https://pith.science/pith/7LWN75W5YDYAFZNL6VPJYXMLZX.json","graph_json":"https://pith.science/api/pith-number/7LWN75W5YDYAFZNL6VPJYXMLZX/graph.json","events_json":"https://pith.science/api/pith-number/7LWN75W5YDYAFZNL6VPJYXMLZX/events.json","paper":"https://pith.science/paper/7LWN75W5"},"agent_actions":{"view_html":"https://pith.science/pith/7LWN75W5YDYAFZNL6VPJYXMLZX","download_json":"https://pith.science/pith/7LWN75W5YDYAFZNL6VPJYXMLZX.json","view_paper":"https://pith.science/paper/7LWN75W5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.05727&json=true","fetch_graph":"https://pith.science/api/pith-number/7LWN75W5YDYAFZNL6VPJYXMLZX/graph.json","fetch_events":"https://pith.science/api/pith-number/7LWN75W5YDYAFZNL6VPJYXMLZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LWN75W5YDYAFZNL6VPJYXMLZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LWN75W5YDYAFZNL6VPJYXMLZX/action/storage_attestation","attest_author":"https://pith.science/pith/7LWN75W5YDYAFZNL6VPJYXMLZX/action/author_attestation","sign_citation":"https://pith.science/pith/7LWN75W5YDYAFZNL6VPJYXMLZX/action/citation_signature","submit_replication":"https://pith.science/pith/7LWN75W5YDYAFZNL6VPJYXMLZX/action/replication_record"}},"created_at":"2026-07-05T07:32:34.562456+00:00","updated_at":"2026-07-05T07:32:34.562456+00:00"}