{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3TNFS76KUONICM3MK5QJLHBFVD","short_pith_number":"pith:3TNFS76K","schema_version":"1.0","canonical_sha256":"dcda597fcaa39a81336c5760959c25a8ce42198f6a266cc1d19a1b2ecc242ff9","source":{"kind":"arxiv","id":"1703.10724","version":2},"attestation_state":"computed","paper":{"title":"N-gram Language Modeling using Recurrent Neural Network Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ciprian Chelba, Mohammad Norouzi, Samy Bengio","submitted_at":"2017-03-31T01:21:40Z","abstract_excerpt":"We investigate the effective memory depth of RNN models by using them for $n$-gram language model (LM) smoothing.\n  Experiments on a small corpus (UPenn Treebank, one million words of training data and 10k vocabulary) have found the LSTM cell with dropout to be the best model for encoding the $n$-gram state when compared with feed-forward and vanilla RNN models. When preserving the sentence independence assumption the LSTM $n$-gram matches the LSTM LM performance for $n=9$ and slightly outperforms it for $n=13$. When allowing dependencies across sentence boundaries, the LSTM $13$-gram almost m"},"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":"1703.10724","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-31T01:21:40Z","cross_cats_sorted":[],"title_canon_sha256":"0d9c1a716746261ab3287454eb5e4aa7a6e79200a0d8d082d0c6e9a727245fba","abstract_canon_sha256":"e30dc31480f1b4c96412ede8d3b01900c24827a127fa145fc60226b22e414020"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:04.768639Z","signature_b64":"so7/SVUD5lBGAbI+L6EQgYw3H48fPRFJplRuRnIvE9/jpiueT9hdpiVs9YDGI13+WSdMdOBAcUBr8SZ4LNdrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcda597fcaa39a81336c5760959c25a8ce42198f6a266cc1d19a1b2ecc242ff9","last_reissued_at":"2026-05-18T00:42:04.767873Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:04.767873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"N-gram Language Modeling using Recurrent Neural Network Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ciprian Chelba, Mohammad Norouzi, Samy Bengio","submitted_at":"2017-03-31T01:21:40Z","abstract_excerpt":"We investigate the effective memory depth of RNN models by using them for $n$-gram language model (LM) smoothing.\n  Experiments on a small corpus (UPenn Treebank, one million words of training data and 10k vocabulary) have found the LSTM cell with dropout to be the best model for encoding the $n$-gram state when compared with feed-forward and vanilla RNN models. When preserving the sentence independence assumption the LSTM $n$-gram matches the LSTM LM performance for $n=9$ and slightly outperforms it for $n=13$. When allowing dependencies across sentence boundaries, the LSTM $13$-gram almost m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10724","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":""},"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":"1703.10724","created_at":"2026-05-18T00:42:04.768002+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.10724v2","created_at":"2026-05-18T00:42:04.768002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10724","created_at":"2026-05-18T00:42:04.768002+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TNFS76KUONI","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TNFS76KUONICM3M","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TNFS76K","created_at":"2026-05-18T12:30:58.224056+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/3TNFS76KUONICM3MK5QJLHBFVD","json":"https://pith.science/pith/3TNFS76KUONICM3MK5QJLHBFVD.json","graph_json":"https://pith.science/api/pith-number/3TNFS76KUONICM3MK5QJLHBFVD/graph.json","events_json":"https://pith.science/api/pith-number/3TNFS76KUONICM3MK5QJLHBFVD/events.json","paper":"https://pith.science/paper/3TNFS76K"},"agent_actions":{"view_html":"https://pith.science/pith/3TNFS76KUONICM3MK5QJLHBFVD","download_json":"https://pith.science/pith/3TNFS76KUONICM3MK5QJLHBFVD.json","view_paper":"https://pith.science/paper/3TNFS76K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.10724&json=true","fetch_graph":"https://pith.science/api/pith-number/3TNFS76KUONICM3MK5QJLHBFVD/graph.json","fetch_events":"https://pith.science/api/pith-number/3TNFS76KUONICM3MK5QJLHBFVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TNFS76KUONICM3MK5QJLHBFVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TNFS76KUONICM3MK5QJLHBFVD/action/storage_attestation","attest_author":"https://pith.science/pith/3TNFS76KUONICM3MK5QJLHBFVD/action/author_attestation","sign_citation":"https://pith.science/pith/3TNFS76KUONICM3MK5QJLHBFVD/action/citation_signature","submit_replication":"https://pith.science/pith/3TNFS76KUONICM3MK5QJLHBFVD/action/replication_record"}},"created_at":"2026-05-18T00:42:04.768002+00:00","updated_at":"2026-05-18T00:42:04.768002+00:00"}