{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DKCX5FPQXW7BPU2RJUUIPGZ522","short_pith_number":"pith:DKCX5FPQ","schema_version":"1.0","canonical_sha256":"1a857e95f0bdbe17d3514d28879b3dd69f9be913938b42aab1682a35b4f39040","source":{"kind":"arxiv","id":"1708.00107","version":2},"attestation_state":"computed","paper":{"title":"Learned in Translation: Contextualized Word Vectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bryan McCann, Caiming Xiong, James Bradbury, Richard Socher","submitted_at":"2017-08-01T00:05:34Z","abstract_excerpt":"Computer vision has benefited from initializing multiple deep layers with weights pretrained on large supervised training sets like ImageNet. Natural language processing (NLP) typically sees initialization of only the lowest layer of deep models with pretrained word vectors. In this paper, we use a deep LSTM encoder from an attentional sequence-to-sequence model trained for machine translation (MT) to contextualize word vectors. We show that adding these context vectors (CoVe) improves performance over using only unsupervised word and character vectors on a wide variety of common NLP tasks: se"},"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":"1708.00107","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T00:05:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"24d41fc2b690dc545f72c7ad46fd339561f78a500cdb421eeb38af8921ef8d37","abstract_canon_sha256":"e2451bd014c4b085dcb7373ea2be03cfc483027f34776e47b3d215975773e0b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:48.774548Z","signature_b64":"D5JGjsBFU2DGY5r4caAul/ma4zP1ayKfnLzH50MbJj+ozRXXbBpOZT3krBp91HR4yZPIVcv9tuW2pf/Z+Q8WCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a857e95f0bdbe17d3514d28879b3dd69f9be913938b42aab1682a35b4f39040","last_reissued_at":"2026-05-18T00:12:48.773865Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:48.773865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learned in Translation: Contextualized Word Vectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bryan McCann, Caiming Xiong, James Bradbury, Richard Socher","submitted_at":"2017-08-01T00:05:34Z","abstract_excerpt":"Computer vision has benefited from initializing multiple deep layers with weights pretrained on large supervised training sets like ImageNet. Natural language processing (NLP) typically sees initialization of only the lowest layer of deep models with pretrained word vectors. In this paper, we use a deep LSTM encoder from an attentional sequence-to-sequence model trained for machine translation (MT) to contextualize word vectors. We show that adding these context vectors (CoVe) improves performance over using only unsupervised word and character vectors on a wide variety of common NLP tasks: se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00107","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":""},"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":"1708.00107","created_at":"2026-05-18T00:12:48.773976+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.00107v2","created_at":"2026-05-18T00:12:48.773976+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00107","created_at":"2026-05-18T00:12:48.773976+00:00"},{"alias_kind":"pith_short_12","alias_value":"DKCX5FPQXW7B","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"DKCX5FPQXW7BPU2R","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"DKCX5FPQ","created_at":"2026-05-18T12:31:10.602751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.10063","citing_title":"FinBERT: Financial Sentiment Analysis with Pre-trained Language Models","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"1909.08053","citing_title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DKCX5FPQXW7BPU2RJUUIPGZ522","json":"https://pith.science/pith/DKCX5FPQXW7BPU2RJUUIPGZ522.json","graph_json":"https://pith.science/api/pith-number/DKCX5FPQXW7BPU2RJUUIPGZ522/graph.json","events_json":"https://pith.science/api/pith-number/DKCX5FPQXW7BPU2RJUUIPGZ522/events.json","paper":"https://pith.science/paper/DKCX5FPQ"},"agent_actions":{"view_html":"https://pith.science/pith/DKCX5FPQXW7BPU2RJUUIPGZ522","download_json":"https://pith.science/pith/DKCX5FPQXW7BPU2RJUUIPGZ522.json","view_paper":"https://pith.science/paper/DKCX5FPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.00107&json=true","fetch_graph":"https://pith.science/api/pith-number/DKCX5FPQXW7BPU2RJUUIPGZ522/graph.json","fetch_events":"https://pith.science/api/pith-number/DKCX5FPQXW7BPU2RJUUIPGZ522/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DKCX5FPQXW7BPU2RJUUIPGZ522/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DKCX5FPQXW7BPU2RJUUIPGZ522/action/storage_attestation","attest_author":"https://pith.science/pith/DKCX5FPQXW7BPU2RJUUIPGZ522/action/author_attestation","sign_citation":"https://pith.science/pith/DKCX5FPQXW7BPU2RJUUIPGZ522/action/citation_signature","submit_replication":"https://pith.science/pith/DKCX5FPQXW7BPU2RJUUIPGZ522/action/replication_record"}},"created_at":"2026-05-18T00:12:48.773976+00:00","updated_at":"2026-05-18T00:12:48.773976+00:00"}