{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:462YVLDZYQRKRTQ4RAJV3GU6SH","short_pith_number":"pith:462YVLDZ","schema_version":"1.0","canonical_sha256":"e7b58aac79c422a8ce1c88135d9a9e91def6e4740ca8d4ec332e0e4e664133a4","source":{"kind":"arxiv","id":"1705.07267","version":2},"attestation_state":"computed","paper":{"title":"Search Engine Guided Non-Parametric Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiatao Gu, Kyunghyun Cho, Victor O.K. Li, Yong Wang","submitted_at":"2017-05-20T06:53:09Z","abstract_excerpt":"In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training. The proposed approach consists of two stages. In the first stage--retrieval stage--, an off-the-shelf, black-box search engine is used to retrieve a small subset of sentence pairs from a training set given a source sentence. These pairs are further filtered based on a fuzzy matching score based on edit distance. In the second stage--translation stage--, a novel translation model, called translation memory enhanced NMT"},"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":"1705.07267","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-20T06:53:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"db42c0cf5466609966cda6510668032a99e0c9b41de2e02fd5d0ea2febea0b79","abstract_canon_sha256":"c7fbda36ca96b5f39ba42ac44ab26968a9d42bcb8dc488236d86410cdcd458ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:46.362415Z","signature_b64":"AR+LWfr6lJ+chlk5C7hwka1YDBG4rWfJgIORqsCr+CTMZE9NxdFH1ERjuoF8amU8W2OrCfinqEUJn7xl1tDhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7b58aac79c422a8ce1c88135d9a9e91def6e4740ca8d4ec332e0e4e664133a4","last_reissued_at":"2026-05-18T00:21:46.361644Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:46.361644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Search Engine Guided Non-Parametric Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiatao Gu, Kyunghyun Cho, Victor O.K. Li, Yong Wang","submitted_at":"2017-05-20T06:53:09Z","abstract_excerpt":"In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training. The proposed approach consists of two stages. In the first stage--retrieval stage--, an off-the-shelf, black-box search engine is used to retrieve a small subset of sentence pairs from a training set given a source sentence. These pairs are further filtered based on a fuzzy matching score based on edit distance. In the second stage--translation stage--, a novel translation model, called translation memory enhanced NMT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07267","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":"1705.07267","created_at":"2026-05-18T00:21:46.361774+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07267v2","created_at":"2026-05-18T00:21:46.361774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07267","created_at":"2026-05-18T00:21:46.361774+00:00"},{"alias_kind":"pith_short_12","alias_value":"462YVLDZYQRK","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"462YVLDZYQRKRTQ4","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"462YVLDZ","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1911.05507","citing_title":"Compressive Transformers for Long-Range Sequence Modelling","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/462YVLDZYQRKRTQ4RAJV3GU6SH","json":"https://pith.science/pith/462YVLDZYQRKRTQ4RAJV3GU6SH.json","graph_json":"https://pith.science/api/pith-number/462YVLDZYQRKRTQ4RAJV3GU6SH/graph.json","events_json":"https://pith.science/api/pith-number/462YVLDZYQRKRTQ4RAJV3GU6SH/events.json","paper":"https://pith.science/paper/462YVLDZ"},"agent_actions":{"view_html":"https://pith.science/pith/462YVLDZYQRKRTQ4RAJV3GU6SH","download_json":"https://pith.science/pith/462YVLDZYQRKRTQ4RAJV3GU6SH.json","view_paper":"https://pith.science/paper/462YVLDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07267&json=true","fetch_graph":"https://pith.science/api/pith-number/462YVLDZYQRKRTQ4RAJV3GU6SH/graph.json","fetch_events":"https://pith.science/api/pith-number/462YVLDZYQRKRTQ4RAJV3GU6SH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/462YVLDZYQRKRTQ4RAJV3GU6SH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/462YVLDZYQRKRTQ4RAJV3GU6SH/action/storage_attestation","attest_author":"https://pith.science/pith/462YVLDZYQRKRTQ4RAJV3GU6SH/action/author_attestation","sign_citation":"https://pith.science/pith/462YVLDZYQRKRTQ4RAJV3GU6SH/action/citation_signature","submit_replication":"https://pith.science/pith/462YVLDZYQRKRTQ4RAJV3GU6SH/action/replication_record"}},"created_at":"2026-05-18T00:21:46.361774+00:00","updated_at":"2026-05-18T00:21:46.361774+00:00"}