{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:WMRYT45SFK5ZYZOHJIAVFOGUDC","short_pith_number":"pith:WMRYT45S","schema_version":"1.0","canonical_sha256":"b32389f3b22abb9c65c74a0152b8d4188c50adbd7b5730202ed8a0b37244c771","source":{"kind":"arxiv","id":"1603.00810","version":3},"attestation_state":"computed","paper":{"title":"Character-based Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CL","authors_text":"Jos\\'e A. R. Fonollosa, Marta R. Costa-juss\\`a","submitted_at":"2016-03-02T18:01:57Z","abstract_excerpt":"Neural Machine Translation (MT) has reached state-of-the-art results. However, one of the main challenges that neural MT still faces is dealing with very large vocabularies and morphologically rich languages. In this paper, we propose a neural MT system using character-based embeddings in combination with convolutional and highway layers to replace the standard lookup-based word representations. The resulting unlimited-vocabulary and affix-aware source word embeddings are tested in a state-of-the-art neural MT based on an attention-based bidirectional recurrent neural network. The proposed MT "},"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":"1603.00810","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-02T18:01:57Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"bc8e25a8271ffa37be4d41f8736980ca42cc4e7ec717601c65ede7038b34a460","abstract_canon_sha256":"0acd2c7a152725f7b537b974ab2a0253fb9ca16b30185dc2088445add6d77480"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:41.076202Z","signature_b64":"muPYMonutWHQQqzW+2qKqJceHuBo0w+6mZlOboEoItTqEMEoHug2nONJVOb5tw316dDlLMemTsmiy2yGncf+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b32389f3b22abb9c65c74a0152b8d4188c50adbd7b5730202ed8a0b37244c771","last_reissued_at":"2026-05-18T01:11:41.075772Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:41.075772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Character-based Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CL","authors_text":"Jos\\'e A. R. Fonollosa, Marta R. Costa-juss\\`a","submitted_at":"2016-03-02T18:01:57Z","abstract_excerpt":"Neural Machine Translation (MT) has reached state-of-the-art results. However, one of the main challenges that neural MT still faces is dealing with very large vocabularies and morphologically rich languages. In this paper, we propose a neural MT system using character-based embeddings in combination with convolutional and highway layers to replace the standard lookup-based word representations. The resulting unlimited-vocabulary and affix-aware source word embeddings are tested in a state-of-the-art neural MT based on an attention-based bidirectional recurrent neural network. The proposed MT "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.00810","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":"1603.00810","created_at":"2026-05-18T01:11:41.075849+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.00810v3","created_at":"2026-05-18T01:11:41.075849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.00810","created_at":"2026-05-18T01:11:41.075849+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMRYT45SFK5Z","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMRYT45SFK5ZYZOH","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMRYT45S","created_at":"2026-05-18T12:30:48.956258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.05019","citing_title":"Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"1609.08144","citing_title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMRYT45SFK5ZYZOHJIAVFOGUDC","json":"https://pith.science/pith/WMRYT45SFK5ZYZOHJIAVFOGUDC.json","graph_json":"https://pith.science/api/pith-number/WMRYT45SFK5ZYZOHJIAVFOGUDC/graph.json","events_json":"https://pith.science/api/pith-number/WMRYT45SFK5ZYZOHJIAVFOGUDC/events.json","paper":"https://pith.science/paper/WMRYT45S"},"agent_actions":{"view_html":"https://pith.science/pith/WMRYT45SFK5ZYZOHJIAVFOGUDC","download_json":"https://pith.science/pith/WMRYT45SFK5ZYZOHJIAVFOGUDC.json","view_paper":"https://pith.science/paper/WMRYT45S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.00810&json=true","fetch_graph":"https://pith.science/api/pith-number/WMRYT45SFK5ZYZOHJIAVFOGUDC/graph.json","fetch_events":"https://pith.science/api/pith-number/WMRYT45SFK5ZYZOHJIAVFOGUDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMRYT45SFK5ZYZOHJIAVFOGUDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMRYT45SFK5ZYZOHJIAVFOGUDC/action/storage_attestation","attest_author":"https://pith.science/pith/WMRYT45SFK5ZYZOHJIAVFOGUDC/action/author_attestation","sign_citation":"https://pith.science/pith/WMRYT45SFK5ZYZOHJIAVFOGUDC/action/citation_signature","submit_replication":"https://pith.science/pith/WMRYT45SFK5ZYZOHJIAVFOGUDC/action/replication_record"}},"created_at":"2026-05-18T01:11:41.075849+00:00","updated_at":"2026-05-18T01:11:41.075849+00:00"}