{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VP2OSY2F5KQHPD252MR6ADNTJL","short_pith_number":"pith:VP2OSY2F","schema_version":"1.0","canonical_sha256":"abf4e96345eaa0778f5dd323e00db34ac97eaab245cc70341995c38e8f53d750","source":{"kind":"arxiv","id":"1805.11189","version":1},"attestation_state":"computed","paper":{"title":"Graph-based Filtering of Out-of-Vocabulary Words for Encoder-Decoder Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hayahide Yamagishi, Mamoru Komachi, Satoru Katsumata, Yukio Matsumura","submitted_at":"2018-05-28T22:09:49Z","abstract_excerpt":"Encoder-decoder models typically only employ words that are frequently used in the training corpus to reduce the computational costs and exclude noise. However, this vocabulary set may still include words that interfere with learning in encoder-decoder models. This paper proposes a method for selecting more suitable words for learning encoders by utilizing not only frequency, but also co-occurrence information, which we capture using the HITS algorithm. We apply our proposed method to two tasks: machine translation and grammatical error correction. For Japanese-to-English translation, this met"},"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":"1805.11189","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-28T22:09:49Z","cross_cats_sorted":[],"title_canon_sha256":"9087059574eec0dc833a3fea4da8bdcb471ac562774d735eeb253e6a400deaa4","abstract_canon_sha256":"3edcfbb39c65e2702cb46638c7a12b2614a04ebd8b16558010f80ac7a05d006b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:43.631868Z","signature_b64":"VR00mlWIkWZr9iOc0pgQ/oBj7yzlvrwKeYrQzMnUt5TbSIMpkR5lDzvi73wVuc59YnUdfH9ePiUwYgCyNjesCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abf4e96345eaa0778f5dd323e00db34ac97eaab245cc70341995c38e8f53d750","last_reissued_at":"2026-05-18T00:14:43.631355Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:43.631355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-based Filtering of Out-of-Vocabulary Words for Encoder-Decoder Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hayahide Yamagishi, Mamoru Komachi, Satoru Katsumata, Yukio Matsumura","submitted_at":"2018-05-28T22:09:49Z","abstract_excerpt":"Encoder-decoder models typically only employ words that are frequently used in the training corpus to reduce the computational costs and exclude noise. However, this vocabulary set may still include words that interfere with learning in encoder-decoder models. This paper proposes a method for selecting more suitable words for learning encoders by utilizing not only frequency, but also co-occurrence information, which we capture using the HITS algorithm. We apply our proposed method to two tasks: machine translation and grammatical error correction. For Japanese-to-English translation, this met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11189","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":"1805.11189","created_at":"2026-05-18T00:14:43.631453+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.11189v1","created_at":"2026-05-18T00:14:43.631453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11189","created_at":"2026-05-18T00:14:43.631453+00:00"},{"alias_kind":"pith_short_12","alias_value":"VP2OSY2F5KQH","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VP2OSY2F5KQHPD25","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VP2OSY2F","created_at":"2026-05-18T12:32:59.047623+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/VP2OSY2F5KQHPD252MR6ADNTJL","json":"https://pith.science/pith/VP2OSY2F5KQHPD252MR6ADNTJL.json","graph_json":"https://pith.science/api/pith-number/VP2OSY2F5KQHPD252MR6ADNTJL/graph.json","events_json":"https://pith.science/api/pith-number/VP2OSY2F5KQHPD252MR6ADNTJL/events.json","paper":"https://pith.science/paper/VP2OSY2F"},"agent_actions":{"view_html":"https://pith.science/pith/VP2OSY2F5KQHPD252MR6ADNTJL","download_json":"https://pith.science/pith/VP2OSY2F5KQHPD252MR6ADNTJL.json","view_paper":"https://pith.science/paper/VP2OSY2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.11189&json=true","fetch_graph":"https://pith.science/api/pith-number/VP2OSY2F5KQHPD252MR6ADNTJL/graph.json","fetch_events":"https://pith.science/api/pith-number/VP2OSY2F5KQHPD252MR6ADNTJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VP2OSY2F5KQHPD252MR6ADNTJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VP2OSY2F5KQHPD252MR6ADNTJL/action/storage_attestation","attest_author":"https://pith.science/pith/VP2OSY2F5KQHPD252MR6ADNTJL/action/author_attestation","sign_citation":"https://pith.science/pith/VP2OSY2F5KQHPD252MR6ADNTJL/action/citation_signature","submit_replication":"https://pith.science/pith/VP2OSY2F5KQHPD252MR6ADNTJL/action/replication_record"}},"created_at":"2026-05-18T00:14:43.631453+00:00","updated_at":"2026-05-18T00:14:43.631453+00:00"}