{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:JDT7W3WQXWRUAPTQOMFDT2PQKU","short_pith_number":"pith:JDT7W3WQ","schema_version":"1.0","canonical_sha256":"48e7fb6ed0bda3403e70730a39e9f055386ed5f2c0c9202324a96e677eff5c9b","source":{"kind":"arxiv","id":"1712.09783","version":3},"attestation_state":"computed","paper":{"title":"Topic Compositional Neural Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Dinghan Shen, Jiaji Huang, Lawrence Carin, Sanjeev Satheesh, Wei Ping, Wenlin Wang, Wenqi Wang, Zhe Gan","submitted_at":"2017-12-28T08:05:48Z","abstract_excerpt":"We propose a Topic Compositional Neural Language Model (TCNLM), a novel method designed to simultaneously capture both the global semantic meaning and the local word ordering structure in a document. The TCNLM learns the global semantic coherence of a document via a neural topic model, and the probability of each learned latent topic is further used to build a Mixture-of-Experts (MoE) language model, where each expert (corresponding to one topic) is a recurrent neural network (RNN) that accounts for learning the local structure of a word sequence. In order to train the MoE model efficiently, a"},"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":"1712.09783","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-12-28T08:05:48Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"43d857ec03e76fc4ef789195ef34769101133b96614f0b2c2b2717b6df8d0025","abstract_canon_sha256":"d279d2c46986f6a1bcab3653e0eb3290c6ac6dfd337ac95f230e72437c870ddc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:39.007626Z","signature_b64":"MXw5OzCEt5GrNrFMozaCfYqAfEjAb4gTrT0w0y7myXG0WUtTGxFMa01be7hZvKjRUQHuoCgdCC895dT12jw8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48e7fb6ed0bda3403e70730a39e9f055386ed5f2c0c9202324a96e677eff5c9b","last_reissued_at":"2026-05-18T00:22:39.007279Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:39.007279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topic Compositional Neural Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Dinghan Shen, Jiaji Huang, Lawrence Carin, Sanjeev Satheesh, Wei Ping, Wenlin Wang, Wenqi Wang, Zhe Gan","submitted_at":"2017-12-28T08:05:48Z","abstract_excerpt":"We propose a Topic Compositional Neural Language Model (TCNLM), a novel method designed to simultaneously capture both the global semantic meaning and the local word ordering structure in a document. The TCNLM learns the global semantic coherence of a document via a neural topic model, and the probability of each learned latent topic is further used to build a Mixture-of-Experts (MoE) language model, where each expert (corresponding to one topic) is a recurrent neural network (RNN) that accounts for learning the local structure of a word sequence. In order to train the MoE model efficiently, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09783","kind":"arxiv","version":3},"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":"1712.09783","created_at":"2026-05-18T00:22:39.007341+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09783v3","created_at":"2026-05-18T00:22:39.007341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09783","created_at":"2026-05-18T00:22:39.007341+00:00"},{"alias_kind":"pith_short_12","alias_value":"JDT7W3WQXWRU","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"JDT7W3WQXWRUAPTQ","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"JDT7W3WQ","created_at":"2026-05-18T12:31:24.725408+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/JDT7W3WQXWRUAPTQOMFDT2PQKU","json":"https://pith.science/pith/JDT7W3WQXWRUAPTQOMFDT2PQKU.json","graph_json":"https://pith.science/api/pith-number/JDT7W3WQXWRUAPTQOMFDT2PQKU/graph.json","events_json":"https://pith.science/api/pith-number/JDT7W3WQXWRUAPTQOMFDT2PQKU/events.json","paper":"https://pith.science/paper/JDT7W3WQ"},"agent_actions":{"view_html":"https://pith.science/pith/JDT7W3WQXWRUAPTQOMFDT2PQKU","download_json":"https://pith.science/pith/JDT7W3WQXWRUAPTQOMFDT2PQKU.json","view_paper":"https://pith.science/paper/JDT7W3WQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09783&json=true","fetch_graph":"https://pith.science/api/pith-number/JDT7W3WQXWRUAPTQOMFDT2PQKU/graph.json","fetch_events":"https://pith.science/api/pith-number/JDT7W3WQXWRUAPTQOMFDT2PQKU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JDT7W3WQXWRUAPTQOMFDT2PQKU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JDT7W3WQXWRUAPTQOMFDT2PQKU/action/storage_attestation","attest_author":"https://pith.science/pith/JDT7W3WQXWRUAPTQOMFDT2PQKU/action/author_attestation","sign_citation":"https://pith.science/pith/JDT7W3WQXWRUAPTQOMFDT2PQKU/action/citation_signature","submit_replication":"https://pith.science/pith/JDT7W3WQXWRUAPTQOMFDT2PQKU/action/replication_record"}},"created_at":"2026-05-18T00:22:39.007341+00:00","updated_at":"2026-05-18T00:22:39.007341+00:00"}