{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MXOVDSLG2TFUQOZ4QCBBY366VP","short_pith_number":"pith:MXOVDSLG","schema_version":"1.0","canonical_sha256":"65dd51c966d4cb483b3c80821c6fdeabc978b3be04fbff1a8d8308cee3286715","source":{"kind":"arxiv","id":"2106.03958","version":2},"attestation_state":"computed","paper":{"title":"Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhijeet Awasthi, Partha Talukdar, Sarvesh Mehtani, Sunita Sarawagi, Vaidehi Patil, Yash Khemchandani","submitted_at":"2021-06-07T20:43:02Z","abstract_excerpt":"Recent research in multilingual language models (LM) has demonstrated their ability to effectively handle multiple languages in a single model. This holds promise for low web-resource languages (LRL) as multilingual models can enable transfer of supervision from high resource languages to LRLs. However, incorporating a new language in an LM still remains a challenge, particularly for languages with limited corpora and in unseen scripts. In this paper we argue that relatedness among languages in a language family may be exploited to overcome some of the corpora limitations of LRLs, and propose "},"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":"2106.03958","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-07T20:43:02Z","cross_cats_sorted":[],"title_canon_sha256":"1b10f8486e10621e56b9cf382d7369ee8bb51363d46cf5c5c22c3d573e9474df","abstract_canon_sha256":"386c6436e119b78c28bffb49e52e05ecd28b2b65c7b559dccffade582043f25f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:46.398176Z","signature_b64":"vID/oLJubkGIe4w6sbC3E4rCvoB2W2KEPxzFctCB0TQWyLkHywVW6xdtMzKdevEUZycinngIPgJ+n257lCopDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65dd51c966d4cb483b3c80821c6fdeabc978b3be04fbff1a8d8308cee3286715","last_reissued_at":"2026-07-05T02:47:46.397757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:46.397757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhijeet Awasthi, Partha Talukdar, Sarvesh Mehtani, Sunita Sarawagi, Vaidehi Patil, Yash Khemchandani","submitted_at":"2021-06-07T20:43:02Z","abstract_excerpt":"Recent research in multilingual language models (LM) has demonstrated their ability to effectively handle multiple languages in a single model. This holds promise for low web-resource languages (LRL) as multilingual models can enable transfer of supervision from high resource languages to LRLs. However, incorporating a new language in an LM still remains a challenge, particularly for languages with limited corpora and in unseen scripts. In this paper we argue that relatedness among languages in a language family may be exploited to overcome some of the corpora limitations of LRLs, and propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03958","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/2106.03958/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":"2106.03958","created_at":"2026-07-05T02:47:46.397818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03958v2","created_at":"2026-07-05T02:47:46.397818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03958","created_at":"2026-07-05T02:47:46.397818+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXOVDSLG2TFU","created_at":"2026-07-05T02:47:46.397818+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXOVDSLG2TFUQOZ4","created_at":"2026-07-05T02:47:46.397818+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXOVDSLG","created_at":"2026-07-05T02:47:46.397818+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/MXOVDSLG2TFUQOZ4QCBBY366VP","json":"https://pith.science/pith/MXOVDSLG2TFUQOZ4QCBBY366VP.json","graph_json":"https://pith.science/api/pith-number/MXOVDSLG2TFUQOZ4QCBBY366VP/graph.json","events_json":"https://pith.science/api/pith-number/MXOVDSLG2TFUQOZ4QCBBY366VP/events.json","paper":"https://pith.science/paper/MXOVDSLG"},"agent_actions":{"view_html":"https://pith.science/pith/MXOVDSLG2TFUQOZ4QCBBY366VP","download_json":"https://pith.science/pith/MXOVDSLG2TFUQOZ4QCBBY366VP.json","view_paper":"https://pith.science/paper/MXOVDSLG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03958&json=true","fetch_graph":"https://pith.science/api/pith-number/MXOVDSLG2TFUQOZ4QCBBY366VP/graph.json","fetch_events":"https://pith.science/api/pith-number/MXOVDSLG2TFUQOZ4QCBBY366VP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXOVDSLG2TFUQOZ4QCBBY366VP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXOVDSLG2TFUQOZ4QCBBY366VP/action/storage_attestation","attest_author":"https://pith.science/pith/MXOVDSLG2TFUQOZ4QCBBY366VP/action/author_attestation","sign_citation":"https://pith.science/pith/MXOVDSLG2TFUQOZ4QCBBY366VP/action/citation_signature","submit_replication":"https://pith.science/pith/MXOVDSLG2TFUQOZ4QCBBY366VP/action/replication_record"}},"created_at":"2026-07-05T02:47:46.397818+00:00","updated_at":"2026-07-05T02:47:46.397818+00:00"}