{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:3QJ7YOAVUUX7YM74RJBVJURXAT","short_pith_number":"pith:3QJ7YOAV","schema_version":"1.0","canonical_sha256":"dc13fc3815a52ffc33fc8a4354d23704f86b98b7b51ebd56b5f2c1776b39114b","source":{"kind":"arxiv","id":"1609.07730","version":2},"attestation_state":"computed","paper":{"title":"Lattice-Based Recurrent Neural Network Encoders for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Jinsong Su, Rongrong Ji, Xiaodong Shi, Yang Liu, Zhixing Tan","submitted_at":"2016-09-25T10:59:01Z","abstract_excerpt":"Neural machine translation (NMT) heavily relies on word-level modelling to learn semantic representations of input sentences. However, for languages without natural word delimiters (e.g., Chinese) where input sentences have to be tokenized first, conventional NMT is confronted with two issues: 1) it is difficult to find an optimal tokenization granularity for source sentence modelling, and 2) errors in 1-best tokenizations may propagate to the encoder of NMT. To handle these issues, we propose word-lattice based Recurrent Neural Network (RNN) encoders for NMT, which generalize the standard RNN"},"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":"1609.07730","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-25T10:59:01Z","cross_cats_sorted":[],"title_canon_sha256":"dd144cc164bba5fb2030359e909e6f6e1c488fb734196601739906c28197f668","abstract_canon_sha256":"6a4c6d980ec22c3a28e2cb242b58e4452bd7975ed0c534402daa89e5fb1d0a81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:28.358118Z","signature_b64":"90ZmzxNUH24NRL9l2JvvwZtnCblqp9VENmi+rZQLVxpcRFVbmvRu81DVXaR6ktJylF2kitV67YFXa9qX9tcxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc13fc3815a52ffc33fc8a4354d23704f86b98b7b51ebd56b5f2c1776b39114b","last_reissued_at":"2026-05-18T00:55:28.357683Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:28.357683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lattice-Based Recurrent Neural Network Encoders for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Jinsong Su, Rongrong Ji, Xiaodong Shi, Yang Liu, Zhixing Tan","submitted_at":"2016-09-25T10:59:01Z","abstract_excerpt":"Neural machine translation (NMT) heavily relies on word-level modelling to learn semantic representations of input sentences. However, for languages without natural word delimiters (e.g., Chinese) where input sentences have to be tokenized first, conventional NMT is confronted with two issues: 1) it is difficult to find an optimal tokenization granularity for source sentence modelling, and 2) errors in 1-best tokenizations may propagate to the encoder of NMT. To handle these issues, we propose word-lattice based Recurrent Neural Network (RNN) encoders for NMT, which generalize the standard RNN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.07730","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":"1609.07730","created_at":"2026-05-18T00:55:28.357742+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.07730v2","created_at":"2026-05-18T00:55:28.357742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.07730","created_at":"2026-05-18T00:55:28.357742+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QJ7YOAVUUX7","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QJ7YOAVUUX7YM74","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QJ7YOAV","created_at":"2026-05-18T12:29:55.572404+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/3QJ7YOAVUUX7YM74RJBVJURXAT","json":"https://pith.science/pith/3QJ7YOAVUUX7YM74RJBVJURXAT.json","graph_json":"https://pith.science/api/pith-number/3QJ7YOAVUUX7YM74RJBVJURXAT/graph.json","events_json":"https://pith.science/api/pith-number/3QJ7YOAVUUX7YM74RJBVJURXAT/events.json","paper":"https://pith.science/paper/3QJ7YOAV"},"agent_actions":{"view_html":"https://pith.science/pith/3QJ7YOAVUUX7YM74RJBVJURXAT","download_json":"https://pith.science/pith/3QJ7YOAVUUX7YM74RJBVJURXAT.json","view_paper":"https://pith.science/paper/3QJ7YOAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.07730&json=true","fetch_graph":"https://pith.science/api/pith-number/3QJ7YOAVUUX7YM74RJBVJURXAT/graph.json","fetch_events":"https://pith.science/api/pith-number/3QJ7YOAVUUX7YM74RJBVJURXAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QJ7YOAVUUX7YM74RJBVJURXAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QJ7YOAVUUX7YM74RJBVJURXAT/action/storage_attestation","attest_author":"https://pith.science/pith/3QJ7YOAVUUX7YM74RJBVJURXAT/action/author_attestation","sign_citation":"https://pith.science/pith/3QJ7YOAVUUX7YM74RJBVJURXAT/action/citation_signature","submit_replication":"https://pith.science/pith/3QJ7YOAVUUX7YM74RJBVJURXAT/action/replication_record"}},"created_at":"2026-05-18T00:55:28.357742+00:00","updated_at":"2026-05-18T00:55:28.357742+00:00"}