{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RRM3EU2QQR3C6BUVHQE2HJZVTQ","short_pith_number":"pith:RRM3EU2Q","schema_version":"1.0","canonical_sha256":"8c59b2535084762f06953c09a3a7359c307c28019bb72bad101e909ceeaa785b","source":{"kind":"arxiv","id":"2008.02385","version":1},"attestation_state":"computed","paper":{"title":"Efficient MDI Adaptation for n-gram Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashish Arora, Dan Povey, Ke Li, Ruizhe Huang, Sanjeev Khudanpur","submitted_at":"2020-08-05T22:21:03Z","abstract_excerpt":"This paper presents an efficient algorithm for n-gram language model adaptation under the minimum discrimination information (MDI) principle, where an out-of-domain language model is adapted to satisfy the constraints of marginal probabilities of the in-domain data. The challenge for MDI language model adaptation is its computational complexity. By taking advantage of the backoff structure of n-gram model and the idea of hierarchical training method, originally proposed for maximum entropy (ME) language models, we show that MDI adaptation can be computed in linear-time complexity to the inputs"},"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":"2008.02385","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-05T22:21:03Z","cross_cats_sorted":[],"title_canon_sha256":"d41a03202d779f4cde2a9c3ad45b52cbb0cb5833cda988af6417b5b8f8bcf22d","abstract_canon_sha256":"46e622a227c456b348773ab919cf63b8148c1aa0bff94ff0823d4b9530721e74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:04.562519Z","signature_b64":"jfdxxOzd0K0vbv2gY7817oijZIzpL+75buqJVuCf6yUBae5O/imjRya+oK1zQu5Oj5RLZ5SC30iALC1HnQtHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c59b2535084762f06953c09a3a7359c307c28019bb72bad101e909ceeaa785b","last_reissued_at":"2026-07-05T01:25:04.562087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:04.562087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient MDI Adaptation for n-gram Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashish Arora, Dan Povey, Ke Li, Ruizhe Huang, Sanjeev Khudanpur","submitted_at":"2020-08-05T22:21:03Z","abstract_excerpt":"This paper presents an efficient algorithm for n-gram language model adaptation under the minimum discrimination information (MDI) principle, where an out-of-domain language model is adapted to satisfy the constraints of marginal probabilities of the in-domain data. The challenge for MDI language model adaptation is its computational complexity. By taking advantage of the backoff structure of n-gram model and the idea of hierarchical training method, originally proposed for maximum entropy (ME) language models, we show that MDI adaptation can be computed in linear-time complexity to the inputs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02385","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/2008.02385/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":"2008.02385","created_at":"2026-07-05T01:25:04.562155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.02385v1","created_at":"2026-07-05T01:25:04.562155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02385","created_at":"2026-07-05T01:25:04.562155+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRM3EU2QQR3C","created_at":"2026-07-05T01:25:04.562155+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRM3EU2QQR3C6BUV","created_at":"2026-07-05T01:25:04.562155+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRM3EU2Q","created_at":"2026-07-05T01:25:04.562155+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/RRM3EU2QQR3C6BUVHQE2HJZVTQ","json":"https://pith.science/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ.json","graph_json":"https://pith.science/api/pith-number/RRM3EU2QQR3C6BUVHQE2HJZVTQ/graph.json","events_json":"https://pith.science/api/pith-number/RRM3EU2QQR3C6BUVHQE2HJZVTQ/events.json","paper":"https://pith.science/paper/RRM3EU2Q"},"agent_actions":{"view_html":"https://pith.science/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ","download_json":"https://pith.science/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ.json","view_paper":"https://pith.science/paper/RRM3EU2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.02385&json=true","fetch_graph":"https://pith.science/api/pith-number/RRM3EU2QQR3C6BUVHQE2HJZVTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/RRM3EU2QQR3C6BUVHQE2HJZVTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ/action/storage_attestation","attest_author":"https://pith.science/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ/action/author_attestation","sign_citation":"https://pith.science/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ/action/citation_signature","submit_replication":"https://pith.science/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ/action/replication_record"}},"created_at":"2026-07-05T01:25:04.562155+00:00","updated_at":"2026-07-05T01:25:04.562155+00:00"}