{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:L2RMGFTMUIPTVQ7T5F55Y7SX46","short_pith_number":"pith:L2RMGFTM","schema_version":"1.0","canonical_sha256":"5ea2c3166ca21f3ac3f3e97bdc7e57e7b5297999989c6b412c0873a48bcfa1f4","source":{"kind":"arxiv","id":"2012.11657","version":2},"attestation_state":"computed","paper":{"title":"Subword Sampling for Low Resource Word Alignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christopher Ringlstetter, Ehsaneddin Asgari, Hinrich Sch\\\"utze, Masoud Jalili Sabet, Philipp Dufter","submitted_at":"2020-12-21T19:47:04Z","abstract_excerpt":"Annotation projection is an important area in NLP that can greatly contribute to creating language resources for low-resource languages. Word alignment plays a key role in this setting. However, most of the existing word alignment methods are designed for a high resource setting in machine translation where millions of parallel sentences are available. This amount reduces to a few thousands of sentences when dealing with low-resource languages failing the existing established IBM models. In this paper, we propose subword sampling-based alignment of text units. This method's hypothesis is that "},"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":"2012.11657","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-21T19:47:04Z","cross_cats_sorted":[],"title_canon_sha256":"c98dda0d105f2d3a15c01b75c95ad7caaace67e692e7c98280f3e9198882e5f9","abstract_canon_sha256":"dbe86ec798881055aba4d0c4ea34d0e8f0c9a839c040519c5a26d5741f95f643"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:52.295795Z","signature_b64":"EB3sN++5MlODjX+4F55TBwJcgL8AxyQGWmR4AcJYKxBz0iv79aajBe2Z+S9G0poMKIi7SakBf4zciI3zq4IrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ea2c3166ca21f3ac3f3e97bdc7e57e7b5297999989c6b412c0873a48bcfa1f4","last_reissued_at":"2026-07-05T02:49:52.295302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:52.295302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Subword Sampling for Low Resource Word Alignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christopher Ringlstetter, Ehsaneddin Asgari, Hinrich Sch\\\"utze, Masoud Jalili Sabet, Philipp Dufter","submitted_at":"2020-12-21T19:47:04Z","abstract_excerpt":"Annotation projection is an important area in NLP that can greatly contribute to creating language resources for low-resource languages. Word alignment plays a key role in this setting. However, most of the existing word alignment methods are designed for a high resource setting in machine translation where millions of parallel sentences are available. This amount reduces to a few thousands of sentences when dealing with low-resource languages failing the existing established IBM models. In this paper, we propose subword sampling-based alignment of text units. This method's hypothesis is that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11657","kind":"arxiv","version":2},"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/2012.11657/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":"2012.11657","created_at":"2026-07-05T02:49:52.295365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.11657v2","created_at":"2026-07-05T02:49:52.295365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11657","created_at":"2026-07-05T02:49:52.295365+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2RMGFTMUIPT","created_at":"2026-07-05T02:49:52.295365+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2RMGFTMUIPTVQ7T","created_at":"2026-07-05T02:49:52.295365+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2RMGFTM","created_at":"2026-07-05T02:49:52.295365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00894","citing_title":"MorphBPE: A Morpho-Aware Tokenizer Bridging Linguistic Complexity for Efficient LLM Training Across Morphologies","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46","json":"https://pith.science/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46.json","graph_json":"https://pith.science/api/pith-number/L2RMGFTMUIPTVQ7T5F55Y7SX46/graph.json","events_json":"https://pith.science/api/pith-number/L2RMGFTMUIPTVQ7T5F55Y7SX46/events.json","paper":"https://pith.science/paper/L2RMGFTM"},"agent_actions":{"view_html":"https://pith.science/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46","download_json":"https://pith.science/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46.json","view_paper":"https://pith.science/paper/L2RMGFTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.11657&json=true","fetch_graph":"https://pith.science/api/pith-number/L2RMGFTMUIPTVQ7T5F55Y7SX46/graph.json","fetch_events":"https://pith.science/api/pith-number/L2RMGFTMUIPTVQ7T5F55Y7SX46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46/action/storage_attestation","attest_author":"https://pith.science/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46/action/author_attestation","sign_citation":"https://pith.science/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46/action/citation_signature","submit_replication":"https://pith.science/pith/L2RMGFTMUIPTVQ7T5F55Y7SX46/action/replication_record"}},"created_at":"2026-07-05T02:49:52.295365+00:00","updated_at":"2026-07-05T02:49:52.295365+00:00"}