{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FL62C774QSWSSZDP6EUKWSOQG7","short_pith_number":"pith:FL62C774","schema_version":"1.0","canonical_sha256":"2afda17ffc84ad29646ff128ab49d037d23a31676ff53c25fa34402568132f92","source":{"kind":"arxiv","id":"1908.11771","version":2},"attestation_state":"computed","paper":{"title":"Encoders Help You Disambiguate Word Senses in Neural Machine Translation","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":"2019-08-30T15:00:19Z","abstract_excerpt":"Neural machine translation (NMT) has achieved new state-of-the-art performance in translating ambiguous words. However, it is still unclear which component dominates the process of disambiguation. In this paper, we explore the ability of NMT encoders and decoders to disambiguate word senses by evaluating hidden states and investigating the distributions of self-attention. We train a classifier to predict whether a translation is correct given the representation of an ambiguous noun. We find that encoder hidden states outperform word embeddings significantly which indicates that encoders adequa"},"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":"1908.11771","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-30T15:00:19Z","cross_cats_sorted":[],"title_canon_sha256":"fc6f6f0b334fb0c6261b1693a6e9113f5845652fa79fed85c554988964b55d46","abstract_canon_sha256":"4feae5a91d25f4dc9d73c5283b205d660a4eb799ce4998bcc36496dd23bb26e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:47.363496Z","signature_b64":"GGEujYZ2zXc7n+95FrUEgm2xINFhuU7lvdUd13C5TTzkV1RtusBzzY+dJQks8QC/9pTujQdJBW2PFUhST0KcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2afda17ffc84ad29646ff128ab49d037d23a31676ff53c25fa34402568132f92","last_reissued_at":"2026-07-05T01:00:47.362967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:47.362967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Encoders Help You Disambiguate Word Senses in Neural Machine Translation","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":"2019-08-30T15:00:19Z","abstract_excerpt":"Neural machine translation (NMT) has achieved new state-of-the-art performance in translating ambiguous words. However, it is still unclear which component dominates the process of disambiguation. In this paper, we explore the ability of NMT encoders and decoders to disambiguate word senses by evaluating hidden states and investigating the distributions of self-attention. We train a classifier to predict whether a translation is correct given the representation of an ambiguous noun. We find that encoder hidden states outperform word embeddings significantly which indicates that encoders adequa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.11771","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.11771/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1908.11771","created_at":"2026-07-05T01:00:47.363028+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.11771v2","created_at":"2026-07-05T01:00:47.363028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.11771","created_at":"2026-07-05T01:00:47.363028+00:00"},{"alias_kind":"pith_short_12","alias_value":"FL62C774QSWS","created_at":"2026-07-05T01:00:47.363028+00:00"},{"alias_kind":"pith_short_16","alias_value":"FL62C774QSWSSZDP","created_at":"2026-07-05T01:00:47.363028+00:00"},{"alias_kind":"pith_short_8","alias_value":"FL62C774","created_at":"2026-07-05T01:00:47.363028+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/FL62C774QSWSSZDP6EUKWSOQG7","json":"https://pith.science/pith/FL62C774QSWSSZDP6EUKWSOQG7.json","graph_json":"https://pith.science/api/pith-number/FL62C774QSWSSZDP6EUKWSOQG7/graph.json","events_json":"https://pith.science/api/pith-number/FL62C774QSWSSZDP6EUKWSOQG7/events.json","paper":"https://pith.science/paper/FL62C774"},"agent_actions":{"view_html":"https://pith.science/pith/FL62C774QSWSSZDP6EUKWSOQG7","download_json":"https://pith.science/pith/FL62C774QSWSSZDP6EUKWSOQG7.json","view_paper":"https://pith.science/paper/FL62C774","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.11771&json=true","fetch_graph":"https://pith.science/api/pith-number/FL62C774QSWSSZDP6EUKWSOQG7/graph.json","fetch_events":"https://pith.science/api/pith-number/FL62C774QSWSSZDP6EUKWSOQG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FL62C774QSWSSZDP6EUKWSOQG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FL62C774QSWSSZDP6EUKWSOQG7/action/storage_attestation","attest_author":"https://pith.science/pith/FL62C774QSWSSZDP6EUKWSOQG7/action/author_attestation","sign_citation":"https://pith.science/pith/FL62C774QSWSSZDP6EUKWSOQG7/action/citation_signature","submit_replication":"https://pith.science/pith/FL62C774QSWSSZDP6EUKWSOQG7/action/replication_record"}},"created_at":"2026-07-05T01:00:47.363028+00:00","updated_at":"2026-07-05T01:00:47.363028+00:00"}