{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RRRVPYJDGE65KZFCQUZBRQFBPT","short_pith_number":"pith:RRRVPYJD","schema_version":"1.0","canonical_sha256":"8c6357e123313dd564a2853218c0a17ce4413f83d757f8bca1652964e6a2219f","source":{"kind":"arxiv","id":"1603.08148","version":3},"attestation_state":"computed","paper":{"title":"Pointing the Unknown Words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Bowen Zhou, Caglar Gulcehre, Ramesh Nallapati, Sungjin Ahn, Yoshua Bengio","submitted_at":"2016-03-26T22:31:57Z","abstract_excerpt":"The problem of rare and unknown words is an important issue that can potentially influence the performance of many NLP systems, including both the traditional count-based and the deep learning models. We propose a novel way to deal with the rare and unseen words for the neural network models using attention. Our model uses two softmax layers in order to predict the next word in conditional language models: one predicts the location of a word in the source sentence, and the other predicts a word in the shortlist vocabulary. At each time-step, the decision of which softmax layer to use choose ad"},"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":"1603.08148","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-26T22:31:57Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"9d7a3ef590097ae924f6d6506bce1eaaec6618e660dbd0d2a2d5023b509aaa9d","abstract_canon_sha256":"217ffca5cf6ac6a80d270f5c83963dc49a72c98fdd739160c5421bef948a68d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:08:25.696827Z","signature_b64":"Xxj6Pz7bm6c51UmQEvWjgv8kybgkokxgCKYavEaMoIGjNt73K4i96MY9FcFLpUr28ytpWoxm7uUYlkbD1HCuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c6357e123313dd564a2853218c0a17ce4413f83d757f8bca1652964e6a2219f","last_reissued_at":"2026-05-18T01:08:25.696150Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:08:25.696150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pointing the Unknown Words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Bowen Zhou, Caglar Gulcehre, Ramesh Nallapati, Sungjin Ahn, Yoshua Bengio","submitted_at":"2016-03-26T22:31:57Z","abstract_excerpt":"The problem of rare and unknown words is an important issue that can potentially influence the performance of many NLP systems, including both the traditional count-based and the deep learning models. We propose a novel way to deal with the rare and unseen words for the neural network models using attention. Our model uses two softmax layers in order to predict the next word in conditional language models: one predicts the location of a word in the source sentence, and the other predicts a word in the shortlist vocabulary. At each time-step, the decision of which softmax layer to use choose ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.08148","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":"1603.08148","created_at":"2026-05-18T01:08:25.696248+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.08148v3","created_at":"2026-05-18T01:08:25.696248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.08148","created_at":"2026-05-18T01:08:25.696248+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRRVPYJDGE65","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRRVPYJDGE65KZFC","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRRVPYJD","created_at":"2026-05-18T12:30:41.710351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1911.05507","citing_title":"Compressive Transformers for Long-Range Sequence Modelling","ref_index":83,"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":18,"is_internal_anchor":false},{"citing_arxiv_id":"1609.07843","citing_title":"Pointer Sentinel Mixture Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRRVPYJDGE65KZFCQUZBRQFBPT","json":"https://pith.science/pith/RRRVPYJDGE65KZFCQUZBRQFBPT.json","graph_json":"https://pith.science/api/pith-number/RRRVPYJDGE65KZFCQUZBRQFBPT/graph.json","events_json":"https://pith.science/api/pith-number/RRRVPYJDGE65KZFCQUZBRQFBPT/events.json","paper":"https://pith.science/paper/RRRVPYJD"},"agent_actions":{"view_html":"https://pith.science/pith/RRRVPYJDGE65KZFCQUZBRQFBPT","download_json":"https://pith.science/pith/RRRVPYJDGE65KZFCQUZBRQFBPT.json","view_paper":"https://pith.science/paper/RRRVPYJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.08148&json=true","fetch_graph":"https://pith.science/api/pith-number/RRRVPYJDGE65KZFCQUZBRQFBPT/graph.json","fetch_events":"https://pith.science/api/pith-number/RRRVPYJDGE65KZFCQUZBRQFBPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRRVPYJDGE65KZFCQUZBRQFBPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRRVPYJDGE65KZFCQUZBRQFBPT/action/storage_attestation","attest_author":"https://pith.science/pith/RRRVPYJDGE65KZFCQUZBRQFBPT/action/author_attestation","sign_citation":"https://pith.science/pith/RRRVPYJDGE65KZFCQUZBRQFBPT/action/citation_signature","submit_replication":"https://pith.science/pith/RRRVPYJDGE65KZFCQUZBRQFBPT/action/replication_record"}},"created_at":"2026-05-18T01:08:25.696248+00:00","updated_at":"2026-05-18T01:08:25.696248+00:00"}