{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:F75DNJYDYM72UG67IPYKTL3WAU","short_pith_number":"pith:F75DNJYD","schema_version":"1.0","canonical_sha256":"2ffa36a703c33faa1bdf43f0a9af7605161aa130c81c476b02754a6119cad769","source":{"kind":"arxiv","id":"1907.08158","version":1},"attestation_state":"computed","paper":{"title":"Understanding Neural Machine Translation by Simplification: The Case of Encoder-free Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gongbo Tang, Joakim Nivre, Rico Sennrich","submitted_at":"2019-07-18T16:59:40Z","abstract_excerpt":"In this paper, we try to understand neural machine translation (NMT) via simplifying NMT architectures and training encoder-free NMT models. In an encoder-free model, the sums of word embeddings and positional embeddings represent the source. The decoder is a standard Transformer or recurrent neural network that directly attends to embeddings via attention mechanisms. Experimental results show (1) that the attention mechanism in encoder-free models acts as a strong feature extractor, (2) that the word embeddings in encoder-free models are competitive to those in conventional models, (3) that n"},"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":"1907.08158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-18T16:59:40Z","cross_cats_sorted":[],"title_canon_sha256":"b4f6f96b98b8c1fbe22a938c3cbe83b91c60ca578b003e26c567dcbf6a853cfc","abstract_canon_sha256":"f2bc73caba485f83fb438ad55aceb28974a9279a34b71b7563d121217982c4ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:14.881185Z","signature_b64":"COkwQ2+X+86o1Y3Wzqnzbb6r8lQ32uFXVRVkrdpJTiw35H1G3uamtsbbUEG6YRY0PAUOKO0h/iXcDmeS517uBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ffa36a703c33faa1bdf43f0a9af7605161aa130c81c476b02754a6119cad769","last_reissued_at":"2026-05-17T23:40:14.880411Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:14.880411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Neural Machine Translation by Simplification: The Case of Encoder-free Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gongbo Tang, Joakim Nivre, Rico Sennrich","submitted_at":"2019-07-18T16:59:40Z","abstract_excerpt":"In this paper, we try to understand neural machine translation (NMT) via simplifying NMT architectures and training encoder-free NMT models. In an encoder-free model, the sums of word embeddings and positional embeddings represent the source. The decoder is a standard Transformer or recurrent neural network that directly attends to embeddings via attention mechanisms. Experimental results show (1) that the attention mechanism in encoder-free models acts as a strong feature extractor, (2) that the word embeddings in encoder-free models are competitive to those in conventional models, (3) that n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.08158","kind":"arxiv","version":1},"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":"1907.08158","created_at":"2026-05-17T23:40:14.880547+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.08158v1","created_at":"2026-05-17T23:40:14.880547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.08158","created_at":"2026-05-17T23:40:14.880547+00:00"},{"alias_kind":"pith_short_12","alias_value":"F75DNJYDYM72","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"F75DNJYDYM72UG67","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"F75DNJYD","created_at":"2026-05-18T12:33:15.570797+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/F75DNJYDYM72UG67IPYKTL3WAU","json":"https://pith.science/pith/F75DNJYDYM72UG67IPYKTL3WAU.json","graph_json":"https://pith.science/api/pith-number/F75DNJYDYM72UG67IPYKTL3WAU/graph.json","events_json":"https://pith.science/api/pith-number/F75DNJYDYM72UG67IPYKTL3WAU/events.json","paper":"https://pith.science/paper/F75DNJYD"},"agent_actions":{"view_html":"https://pith.science/pith/F75DNJYDYM72UG67IPYKTL3WAU","download_json":"https://pith.science/pith/F75DNJYDYM72UG67IPYKTL3WAU.json","view_paper":"https://pith.science/paper/F75DNJYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.08158&json=true","fetch_graph":"https://pith.science/api/pith-number/F75DNJYDYM72UG67IPYKTL3WAU/graph.json","fetch_events":"https://pith.science/api/pith-number/F75DNJYDYM72UG67IPYKTL3WAU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F75DNJYDYM72UG67IPYKTL3WAU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F75DNJYDYM72UG67IPYKTL3WAU/action/storage_attestation","attest_author":"https://pith.science/pith/F75DNJYDYM72UG67IPYKTL3WAU/action/author_attestation","sign_citation":"https://pith.science/pith/F75DNJYDYM72UG67IPYKTL3WAU/action/citation_signature","submit_replication":"https://pith.science/pith/F75DNJYDYM72UG67IPYKTL3WAU/action/replication_record"}},"created_at":"2026-05-17T23:40:14.880547+00:00","updated_at":"2026-05-17T23:40:14.880547+00:00"}