{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YVMLRDTAZMCF4PYGG45FJQPIVO","short_pith_number":"pith:YVMLRDTA","schema_version":"1.0","canonical_sha256":"c558b88e60cb045e3f06373a54c1e8aba267b79b7e35ee0ab5f6f9caf94c0269","source":{"kind":"arxiv","id":"1810.02268","version":3},"attestation_state":"computed","paper":{"title":"A Large-Scale Test Set for the Evaluation of Context-Aware Pronoun Translation in Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Annette Rios, Elena Voita, Mathias M\\\"uller, Rico Sennrich","submitted_at":"2018-10-04T15:06:27Z","abstract_excerpt":"The translation of pronouns presents a special challenge to machine translation to this day, since it often requires context outside the current sentence. Recent work on models that have access to information across sentence boundaries has seen only moderate improvements in terms of automatic evaluation metrics such as BLEU. However, metrics that quantify the overall translation quality are ill-equipped to measure gains from additional context. We argue that a different kind of evaluation is needed to assess how well models translate inter-sentential phenomena such as pronouns. This paper ther"},"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":"1810.02268","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-04T15:06:27Z","cross_cats_sorted":[],"title_canon_sha256":"7ac5ea3808908144bb3729569cee9869a18fa42e976d9d6453539e6866b5ec86","abstract_canon_sha256":"bb70e97fe476b23f5bcbab00c0a368b4cdb72ccdf7117d2575609dc013aeff53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:58.843590Z","signature_b64":"dXULhADEd7/9PJNchTsZRIuHc3q1qKMNFCH1NxdbFfznCx+LFZO6s3UDv/suySSBBMaMDi/paxNxxtGV/qENAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c558b88e60cb045e3f06373a54c1e8aba267b79b7e35ee0ab5f6f9caf94c0269","last_reissued_at":"2026-05-17T23:51:58.843214Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:58.843214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Large-Scale Test Set for the Evaluation of Context-Aware Pronoun Translation in Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Annette Rios, Elena Voita, Mathias M\\\"uller, Rico Sennrich","submitted_at":"2018-10-04T15:06:27Z","abstract_excerpt":"The translation of pronouns presents a special challenge to machine translation to this day, since it often requires context outside the current sentence. Recent work on models that have access to information across sentence boundaries has seen only moderate improvements in terms of automatic evaluation metrics such as BLEU. However, metrics that quantify the overall translation quality are ill-equipped to measure gains from additional context. We argue that a different kind of evaluation is needed to assess how well models translate inter-sentential phenomena such as pronouns. This paper ther"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.02268","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":"1810.02268","created_at":"2026-05-17T23:51:58.843272+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.02268v3","created_at":"2026-05-17T23:51:58.843272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.02268","created_at":"2026-05-17T23:51:58.843272+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVMLRDTAZMCF","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVMLRDTAZMCF4PYG","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVMLRDTA","created_at":"2026-05-18T12:33:04.347982+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/YVMLRDTAZMCF4PYGG45FJQPIVO","json":"https://pith.science/pith/YVMLRDTAZMCF4PYGG45FJQPIVO.json","graph_json":"https://pith.science/api/pith-number/YVMLRDTAZMCF4PYGG45FJQPIVO/graph.json","events_json":"https://pith.science/api/pith-number/YVMLRDTAZMCF4PYGG45FJQPIVO/events.json","paper":"https://pith.science/paper/YVMLRDTA"},"agent_actions":{"view_html":"https://pith.science/pith/YVMLRDTAZMCF4PYGG45FJQPIVO","download_json":"https://pith.science/pith/YVMLRDTAZMCF4PYGG45FJQPIVO.json","view_paper":"https://pith.science/paper/YVMLRDTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.02268&json=true","fetch_graph":"https://pith.science/api/pith-number/YVMLRDTAZMCF4PYGG45FJQPIVO/graph.json","fetch_events":"https://pith.science/api/pith-number/YVMLRDTAZMCF4PYGG45FJQPIVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVMLRDTAZMCF4PYGG45FJQPIVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVMLRDTAZMCF4PYGG45FJQPIVO/action/storage_attestation","attest_author":"https://pith.science/pith/YVMLRDTAZMCF4PYGG45FJQPIVO/action/author_attestation","sign_citation":"https://pith.science/pith/YVMLRDTAZMCF4PYGG45FJQPIVO/action/citation_signature","submit_replication":"https://pith.science/pith/YVMLRDTAZMCF4PYGG45FJQPIVO/action/replication_record"}},"created_at":"2026-05-17T23:51:58.843272+00:00","updated_at":"2026-05-17T23:51:58.843272+00:00"}