{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MLHXIDK4DGL7DXWEFLX36QCG4D","short_pith_number":"pith:MLHXIDK4","schema_version":"1.0","canonical_sha256":"62cf740d5c1997f1dec42aefbf4046e0fcf089c02a3c9b7fee4cdb563e3b8ec5","source":{"kind":"arxiv","id":"1906.00114","version":1},"attestation_state":"computed","paper":{"title":"Examining Structure of Word Embeddings with PCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Tom\\'a\\v{s} Musil","submitted_at":"2019-05-31T22:47:56Z","abstract_excerpt":"In this paper we compare structure of Czech word embeddings for English-Czech neural machine translation (NMT), word2vec and sentiment analysis. We show that although it is possible to successfully predict part of speech (POS) tags from word embeddings of word2vec and various translation models, not all of the embedding spaces show the same structure. The information about POS is present in word2vec embeddings, but the high degree of organization by POS in the NMT decoder suggests that this information is more important for machine translation and therefore the NMT model represents it in more "},"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":"1906.00114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-31T22:47:56Z","cross_cats_sorted":[],"title_canon_sha256":"57c96509edec8181635996ae5eb681480ebee236f7a55110da13c4833c4f84ab","abstract_canon_sha256":"23ef0064c16240b7ac7883b0a064570d4532735d8f5e67647d217b81ea92a3cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:28.151080Z","signature_b64":"DCFjlF27Yi+fmipYINidVfIBFmg/NSJaMkFczJTtRLxQ/uZUnPXEbNIWhe/vyJBx/SymxbTtMeQR/iSc7EybDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62cf740d5c1997f1dec42aefbf4046e0fcf089c02a3c9b7fee4cdb563e3b8ec5","last_reissued_at":"2026-05-17T23:44:28.150491Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:28.150491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Examining Structure of Word Embeddings with PCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Tom\\'a\\v{s} Musil","submitted_at":"2019-05-31T22:47:56Z","abstract_excerpt":"In this paper we compare structure of Czech word embeddings for English-Czech neural machine translation (NMT), word2vec and sentiment analysis. We show that although it is possible to successfully predict part of speech (POS) tags from word embeddings of word2vec and various translation models, not all of the embedding spaces show the same structure. The information about POS is present in word2vec embeddings, but the high degree of organization by POS in the NMT decoder suggests that this information is more important for machine translation and therefore the NMT model represents it in more "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00114","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":"1906.00114","created_at":"2026-05-17T23:44:28.150579+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00114v1","created_at":"2026-05-17T23:44:28.150579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00114","created_at":"2026-05-17T23:44:28.150579+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLHXIDK4DGL7","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLHXIDK4DGL7DXWE","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLHXIDK4","created_at":"2026-05-18T12:33:21.387695+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/MLHXIDK4DGL7DXWEFLX36QCG4D","json":"https://pith.science/pith/MLHXIDK4DGL7DXWEFLX36QCG4D.json","graph_json":"https://pith.science/api/pith-number/MLHXIDK4DGL7DXWEFLX36QCG4D/graph.json","events_json":"https://pith.science/api/pith-number/MLHXIDK4DGL7DXWEFLX36QCG4D/events.json","paper":"https://pith.science/paper/MLHXIDK4"},"agent_actions":{"view_html":"https://pith.science/pith/MLHXIDK4DGL7DXWEFLX36QCG4D","download_json":"https://pith.science/pith/MLHXIDK4DGL7DXWEFLX36QCG4D.json","view_paper":"https://pith.science/paper/MLHXIDK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00114&json=true","fetch_graph":"https://pith.science/api/pith-number/MLHXIDK4DGL7DXWEFLX36QCG4D/graph.json","fetch_events":"https://pith.science/api/pith-number/MLHXIDK4DGL7DXWEFLX36QCG4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLHXIDK4DGL7DXWEFLX36QCG4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLHXIDK4DGL7DXWEFLX36QCG4D/action/storage_attestation","attest_author":"https://pith.science/pith/MLHXIDK4DGL7DXWEFLX36QCG4D/action/author_attestation","sign_citation":"https://pith.science/pith/MLHXIDK4DGL7DXWEFLX36QCG4D/action/citation_signature","submit_replication":"https://pith.science/pith/MLHXIDK4DGL7DXWEFLX36QCG4D/action/replication_record"}},"created_at":"2026-05-17T23:44:28.150579+00:00","updated_at":"2026-05-17T23:44:28.150579+00:00"}