{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:LPOMVSL4EM6HJSP6BTEBSNLY4P","short_pith_number":"pith:LPOMVSL4","schema_version":"1.0","canonical_sha256":"5bdccac97c233c74c9fe0cc8193578e3e4d571aef31e74d8b89a9cca147abe6d","source":{"kind":"arxiv","id":"1603.09170","version":5},"attestation_state":"computed","paper":{"title":"Model Interpolation with Trans-dimensional Random Field Language Models for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Akinori Kawamura, Bin Wang, Yong He, Zhijian Ou","submitted_at":"2016-03-30T13:09:20Z","abstract_excerpt":"The dominant language models (LMs) such as n-gram and neural network (NN) models represent sentence probabilities in terms of conditionals. In contrast, a new trans-dimensional random field (TRF) LM has been recently introduced to show superior performances, where the whole sentence is modeled as a random field. In this paper, we examine how the TRF models can be interpolated with the NN models, and obtain 12.1\\% and 17.9\\% relative error rate reductions over 6-gram LMs for English and Chinese speech recognition respectively through log-linear combination."},"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":"1603.09170","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-30T13:09:20Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"af5c401697334c7954f6e83fcd71d18575cec3f6c251ea00445613bef37d07ae","abstract_canon_sha256":"da954f2256eb6f7de3278e11756be0f804cf3ab10805cb8d9ceb34dd443be2af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:08:25.678998Z","signature_b64":"uYXY3nyEvczOolHYrzNXawRGKPsf6JjgY9F40F1YniXDtCeVl8/D8QGn6f+KeRQnibHClKZJWVQ5QFfiCX+9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bdccac97c233c74c9fe0cc8193578e3e4d571aef31e74d8b89a9cca147abe6d","last_reissued_at":"2026-05-18T01:08:25.678346Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:08:25.678346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model Interpolation with Trans-dimensional Random Field Language Models for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Akinori Kawamura, Bin Wang, Yong He, Zhijian Ou","submitted_at":"2016-03-30T13:09:20Z","abstract_excerpt":"The dominant language models (LMs) such as n-gram and neural network (NN) models represent sentence probabilities in terms of conditionals. In contrast, a new trans-dimensional random field (TRF) LM has been recently introduced to show superior performances, where the whole sentence is modeled as a random field. In this paper, we examine how the TRF models can be interpolated with the NN models, and obtain 12.1\\% and 17.9\\% relative error rate reductions over 6-gram LMs for English and Chinese speech recognition respectively through log-linear combination."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.09170","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1603.09170","created_at":"2026-05-18T01:08:25.678438+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.09170v5","created_at":"2026-05-18T01:08:25.678438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.09170","created_at":"2026-05-18T01:08:25.678438+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPOMVSL4EM6H","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPOMVSL4EM6HJSP6","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPOMVSL4","created_at":"2026-05-18T12:30:29.479603+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/LPOMVSL4EM6HJSP6BTEBSNLY4P","json":"https://pith.science/pith/LPOMVSL4EM6HJSP6BTEBSNLY4P.json","graph_json":"https://pith.science/api/pith-number/LPOMVSL4EM6HJSP6BTEBSNLY4P/graph.json","events_json":"https://pith.science/api/pith-number/LPOMVSL4EM6HJSP6BTEBSNLY4P/events.json","paper":"https://pith.science/paper/LPOMVSL4"},"agent_actions":{"view_html":"https://pith.science/pith/LPOMVSL4EM6HJSP6BTEBSNLY4P","download_json":"https://pith.science/pith/LPOMVSL4EM6HJSP6BTEBSNLY4P.json","view_paper":"https://pith.science/paper/LPOMVSL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.09170&json=true","fetch_graph":"https://pith.science/api/pith-number/LPOMVSL4EM6HJSP6BTEBSNLY4P/graph.json","fetch_events":"https://pith.science/api/pith-number/LPOMVSL4EM6HJSP6BTEBSNLY4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPOMVSL4EM6HJSP6BTEBSNLY4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPOMVSL4EM6HJSP6BTEBSNLY4P/action/storage_attestation","attest_author":"https://pith.science/pith/LPOMVSL4EM6HJSP6BTEBSNLY4P/action/author_attestation","sign_citation":"https://pith.science/pith/LPOMVSL4EM6HJSP6BTEBSNLY4P/action/citation_signature","submit_replication":"https://pith.science/pith/LPOMVSL4EM6HJSP6BTEBSNLY4P/action/replication_record"}},"created_at":"2026-05-18T01:08:25.678438+00:00","updated_at":"2026-05-18T01:08:25.678438+00:00"}