{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NSD4MLLGKN5OAF2YFC743W6YX4","short_pith_number":"pith:NSD4MLLG","schema_version":"1.0","canonical_sha256":"6c87c62d66537ae0175828bfcddbd8bf04a3a57af52ce788bb4a803137d174c4","source":{"kind":"arxiv","id":"1710.01329","version":3},"attestation_state":"computed","paper":{"title":"Improving Lexical Choice in Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Chiang, Toan Q. Nguyen","submitted_at":"2017-10-03T18:15:10Z","abstract_excerpt":"We explore two solutions to the problem of mistranslating rare words in neural machine translation. First, we argue that the standard output layer, which computes the inner product of a vector representing the context with all possible output word embeddings, rewards frequent words disproportionately, and we propose to fix the norms of both vectors to a constant value. Second, we integrate a simple lexical module which is jointly trained with the rest of the model. We evaluate our approaches on eight language pairs with data sizes ranging from 100k to 8M words, and achieve improvements of up t"},"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":"1710.01329","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-03T18:15:10Z","cross_cats_sorted":[],"title_canon_sha256":"8469b62548def7629a1510c35ab565c182928e1d7880b63c920739e1536b87f3","abstract_canon_sha256":"6c4c510fc814ee234f9da6288000b86ee4b77673b8463a963c5c248442c77301"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:09.460789Z","signature_b64":"VExggtzNAkYl6YN5QJYPsPzZAXhRADfsvLHUY0j+PhOx/8piYPmVUCBkzbHTqPmIcYIIL/0Tt67SXcdgucYdDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c87c62d66537ae0175828bfcddbd8bf04a3a57af52ce788bb4a803137d174c4","last_reissued_at":"2026-05-18T00:18:09.460282Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:09.460282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Lexical Choice in Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Chiang, Toan Q. Nguyen","submitted_at":"2017-10-03T18:15:10Z","abstract_excerpt":"We explore two solutions to the problem of mistranslating rare words in neural machine translation. First, we argue that the standard output layer, which computes the inner product of a vector representing the context with all possible output word embeddings, rewards frequent words disproportionately, and we propose to fix the norms of both vectors to a constant value. Second, we integrate a simple lexical module which is jointly trained with the rest of the model. We evaluate our approaches on eight language pairs with data sizes ranging from 100k to 8M words, and achieve improvements of up t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.01329","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":"1710.01329","created_at":"2026-05-18T00:18:09.460368+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.01329v3","created_at":"2026-05-18T00:18:09.460368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.01329","created_at":"2026-05-18T00:18:09.460368+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSD4MLLGKN5O","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSD4MLLGKN5OAF2Y","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSD4MLLG","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.12284","citing_title":"Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"1910.07467","citing_title":"Root Mean Square Layer Normalization","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NSD4MLLGKN5OAF2YFC743W6YX4","json":"https://pith.science/pith/NSD4MLLGKN5OAF2YFC743W6YX4.json","graph_json":"https://pith.science/api/pith-number/NSD4MLLGKN5OAF2YFC743W6YX4/graph.json","events_json":"https://pith.science/api/pith-number/NSD4MLLGKN5OAF2YFC743W6YX4/events.json","paper":"https://pith.science/paper/NSD4MLLG"},"agent_actions":{"view_html":"https://pith.science/pith/NSD4MLLGKN5OAF2YFC743W6YX4","download_json":"https://pith.science/pith/NSD4MLLGKN5OAF2YFC743W6YX4.json","view_paper":"https://pith.science/paper/NSD4MLLG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.01329&json=true","fetch_graph":"https://pith.science/api/pith-number/NSD4MLLGKN5OAF2YFC743W6YX4/graph.json","fetch_events":"https://pith.science/api/pith-number/NSD4MLLGKN5OAF2YFC743W6YX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSD4MLLGKN5OAF2YFC743W6YX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSD4MLLGKN5OAF2YFC743W6YX4/action/storage_attestation","attest_author":"https://pith.science/pith/NSD4MLLGKN5OAF2YFC743W6YX4/action/author_attestation","sign_citation":"https://pith.science/pith/NSD4MLLGKN5OAF2YFC743W6YX4/action/citation_signature","submit_replication":"https://pith.science/pith/NSD4MLLGKN5OAF2YFC743W6YX4/action/replication_record"}},"created_at":"2026-05-18T00:18:09.460368+00:00","updated_at":"2026-05-18T00:18:09.460368+00:00"}