{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KFMFPL27XUAEFEJUDIUZFSW2AS","short_pith_number":"pith:KFMFPL27","schema_version":"1.0","canonical_sha256":"515857af5fbd004291341a2992cada048169b5f588fa8a1c54cbe057e31e12af","source":{"kind":"arxiv","id":"1810.10927","version":2},"attestation_state":"computed","paper":{"title":"Bayesian Compression for Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Dmitry Vetrov, Ekaterina Lobacheva, Nadezhda Chirkova","submitted_at":"2018-10-25T15:27:23Z","abstract_excerpt":"In natural language processing, a lot of the tasks are successfully solved with recurrent neural networks, but such models have a huge number of parameters. The majority of these parameters are often concentrated in the embedding layer, which size grows proportionally to the vocabulary length. We propose a Bayesian sparsification technique for RNNs which allows compressing the RNN dozens or hundreds of times without time-consuming hyperparameters tuning. We also generalize the model for vocabulary sparsification to filter out unnecessary words and compress the RNN even further. We show that th"},"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":"1810.10927","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-25T15:27:23Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"9cdc1d564399fe0300de9c453c307fa5d670f813e7cb0b1a25d49ce0ed2d102c","abstract_canon_sha256":"c861a6df8cefbc75e27ec3f990e09e4590ca5dedfc6ece6282c628d7ec431f21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:30.287558Z","signature_b64":"taxC6RxjhiuYklVagZ1m70gXXfa6Vr31R6beYskY+TJN3k8EsIq1x07S0M40BdUCupt9mQh35thBAnDj5VbODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"515857af5fbd004291341a2992cada048169b5f588fa8a1c54cbe057e31e12af","last_reissued_at":"2026-05-17T23:58:30.286900Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:30.286900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Compression for Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Dmitry Vetrov, Ekaterina Lobacheva, Nadezhda Chirkova","submitted_at":"2018-10-25T15:27:23Z","abstract_excerpt":"In natural language processing, a lot of the tasks are successfully solved with recurrent neural networks, but such models have a huge number of parameters. The majority of these parameters are often concentrated in the embedding layer, which size grows proportionally to the vocabulary length. We propose a Bayesian sparsification technique for RNNs which allows compressing the RNN dozens or hundreds of times without time-consuming hyperparameters tuning. We also generalize the model for vocabulary sparsification to filter out unnecessary words and compress the RNN even further. We show that th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10927","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":"1810.10927","created_at":"2026-05-17T23:58:30.287004+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.10927v2","created_at":"2026-05-17T23:58:30.287004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10927","created_at":"2026-05-17T23:58:30.287004+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFMFPL27XUAE","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFMFPL27XUAEFEJU","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFMFPL27","created_at":"2026-05-18T12:32:33.847187+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/KFMFPL27XUAEFEJUDIUZFSW2AS","json":"https://pith.science/pith/KFMFPL27XUAEFEJUDIUZFSW2AS.json","graph_json":"https://pith.science/api/pith-number/KFMFPL27XUAEFEJUDIUZFSW2AS/graph.json","events_json":"https://pith.science/api/pith-number/KFMFPL27XUAEFEJUDIUZFSW2AS/events.json","paper":"https://pith.science/paper/KFMFPL27"},"agent_actions":{"view_html":"https://pith.science/pith/KFMFPL27XUAEFEJUDIUZFSW2AS","download_json":"https://pith.science/pith/KFMFPL27XUAEFEJUDIUZFSW2AS.json","view_paper":"https://pith.science/paper/KFMFPL27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.10927&json=true","fetch_graph":"https://pith.science/api/pith-number/KFMFPL27XUAEFEJUDIUZFSW2AS/graph.json","fetch_events":"https://pith.science/api/pith-number/KFMFPL27XUAEFEJUDIUZFSW2AS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFMFPL27XUAEFEJUDIUZFSW2AS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFMFPL27XUAEFEJUDIUZFSW2AS/action/storage_attestation","attest_author":"https://pith.science/pith/KFMFPL27XUAEFEJUDIUZFSW2AS/action/author_attestation","sign_citation":"https://pith.science/pith/KFMFPL27XUAEFEJUDIUZFSW2AS/action/citation_signature","submit_replication":"https://pith.science/pith/KFMFPL27XUAEFEJUDIUZFSW2AS/action/replication_record"}},"created_at":"2026-05-17T23:58:30.287004+00:00","updated_at":"2026-05-17T23:58:30.287004+00:00"}