{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:VORQQRMQ3YPHXTMDWF5SFXUPJF","short_pith_number":"pith:VORQQRMQ","schema_version":"1.0","canonical_sha256":"aba3084590de1e7bcd83b17b22de8f496e603115d2af77ab5be5d8e55c517f81","source":{"kind":"arxiv","id":"1607.00970","version":2},"attestation_state":"computed","paper":{"title":"Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ge Li, Lili Mou, Lu Zhang, Rui Yan, Yiping Song, Zhi Jin","submitted_at":"2016-07-04T17:42:52Z","abstract_excerpt":"Using neural networks to generate replies in human-computer dialogue systems is attracting increasing attention over the past few years. However, the performance is not satisfactory: the neural network tends to generate safe, universally relevant replies which carry little meaning. In this paper, we propose a content-introducing approach to neural network-based generative dialogue systems. We first use pointwise mutual information (PMI) to predict a noun as a keyword, reflecting the main gist of the reply. We then propose seq2BF, a \"sequence to backward and forward sequences\" model, which gene"},"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":"1607.00970","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-04T17:42:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7f76f3134ed1c670488e0b8ffa0130e86d718f7422e0e67f7b822642f3dc89ab","abstract_canon_sha256":"a407f50806e5f103903f2e30e4ae50a5504ee8b492367a6e7f62e7e1cc68f7fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:02:23.501481Z","signature_b64":"PH1taOSxvohGYTNbyXYJb3c+iLwBIbvx6x8NAwiGORxgzewj9hDtx+8J1/E96AaDoiX5IaoFdV8cT/FOuvHTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aba3084590de1e7bcd83b17b22de8f496e603115d2af77ab5be5d8e55c517f81","last_reissued_at":"2026-05-18T01:02:23.500816Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:02:23.500816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ge Li, Lili Mou, Lu Zhang, Rui Yan, Yiping Song, Zhi Jin","submitted_at":"2016-07-04T17:42:52Z","abstract_excerpt":"Using neural networks to generate replies in human-computer dialogue systems is attracting increasing attention over the past few years. However, the performance is not satisfactory: the neural network tends to generate safe, universally relevant replies which carry little meaning. In this paper, we propose a content-introducing approach to neural network-based generative dialogue systems. We first use pointwise mutual information (PMI) to predict a noun as a keyword, reflecting the main gist of the reply. We then propose seq2BF, a \"sequence to backward and forward sequences\" model, which gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.00970","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":"1607.00970","created_at":"2026-05-18T01:02:23.500909+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.00970v2","created_at":"2026-05-18T01:02:23.500909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.00970","created_at":"2026-05-18T01:02:23.500909+00:00"},{"alias_kind":"pith_short_12","alias_value":"VORQQRMQ3YPH","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_16","alias_value":"VORQQRMQ3YPHXTMD","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_8","alias_value":"VORQQRMQ","created_at":"2026-05-18T12:30:48.956258+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/VORQQRMQ3YPHXTMDWF5SFXUPJF","json":"https://pith.science/pith/VORQQRMQ3YPHXTMDWF5SFXUPJF.json","graph_json":"https://pith.science/api/pith-number/VORQQRMQ3YPHXTMDWF5SFXUPJF/graph.json","events_json":"https://pith.science/api/pith-number/VORQQRMQ3YPHXTMDWF5SFXUPJF/events.json","paper":"https://pith.science/paper/VORQQRMQ"},"agent_actions":{"view_html":"https://pith.science/pith/VORQQRMQ3YPHXTMDWF5SFXUPJF","download_json":"https://pith.science/pith/VORQQRMQ3YPHXTMDWF5SFXUPJF.json","view_paper":"https://pith.science/paper/VORQQRMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.00970&json=true","fetch_graph":"https://pith.science/api/pith-number/VORQQRMQ3YPHXTMDWF5SFXUPJF/graph.json","fetch_events":"https://pith.science/api/pith-number/VORQQRMQ3YPHXTMDWF5SFXUPJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VORQQRMQ3YPHXTMDWF5SFXUPJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VORQQRMQ3YPHXTMDWF5SFXUPJF/action/storage_attestation","attest_author":"https://pith.science/pith/VORQQRMQ3YPHXTMDWF5SFXUPJF/action/author_attestation","sign_citation":"https://pith.science/pith/VORQQRMQ3YPHXTMDWF5SFXUPJF/action/citation_signature","submit_replication":"https://pith.science/pith/VORQQRMQ3YPHXTMDWF5SFXUPJF/action/replication_record"}},"created_at":"2026-05-18T01:02:23.500909+00:00","updated_at":"2026-05-18T01:02:23.500909+00:00"}