{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3ASQZWXNRC573EK4NQBXC27LTD","short_pith_number":"pith:3ASQZWXN","schema_version":"1.0","canonical_sha256":"d8250cdaed88bbfd915c6c03716beb98da492e3c83001f6d4552d985135b373c","source":{"kind":"arxiv","id":"1902.00613","version":1},"attestation_state":"computed","paper":{"title":"Understanding Composition of Word Embeddings via Tensor Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abraham Frandsen, Rong Ge","submitted_at":"2019-02-02T01:34:56Z","abstract_excerpt":"Word embedding is a powerful tool in natural language processing. In this paper we consider the problem of word embedding composition \\--- given vector representations of two words, compute a vector for the entire phrase. We give a generative model that can capture specific syntactic relations between words. Under our model, we prove that the correlations between three words (measured by their PMI) form a tensor that has an approximate low rank Tucker decomposition. The result of the Tucker decomposition gives the word embeddings as well as a core tensor, which can be used to produce better co"},"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":"1902.00613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-02T01:34:56Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"b8c22c63e5e2f221c38cc26912b2ed817dfa6ffe356426d9a09bd4ae4f26e2f1","abstract_canon_sha256":"bd9bdcebd2ae8229fd69a27825a3e7c194d48b14a4047fc43e3d173ec50dc58a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:52.674932Z","signature_b64":"I9CONk+vv/uIoD/PbIpRzeJfSitN04caQDCyArPyomH4eTpwLdLRomGcE509QnKZgenliyK8KtNB/l3P/My5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8250cdaed88bbfd915c6c03716beb98da492e3c83001f6d4552d985135b373c","last_reissued_at":"2026-05-17T23:54:52.674367Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:52.674367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Composition of Word Embeddings via Tensor Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abraham Frandsen, Rong Ge","submitted_at":"2019-02-02T01:34:56Z","abstract_excerpt":"Word embedding is a powerful tool in natural language processing. In this paper we consider the problem of word embedding composition \\--- given vector representations of two words, compute a vector for the entire phrase. We give a generative model that can capture specific syntactic relations between words. Under our model, we prove that the correlations between three words (measured by their PMI) form a tensor that has an approximate low rank Tucker decomposition. The result of the Tucker decomposition gives the word embeddings as well as a core tensor, which can be used to produce better co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00613","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":"1902.00613","created_at":"2026-05-17T23:54:52.674464+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.00613v1","created_at":"2026-05-17T23:54:52.674464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00613","created_at":"2026-05-17T23:54:52.674464+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ASQZWXNRC57","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ASQZWXNRC573EK4","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ASQZWXN","created_at":"2026-05-18T12:33:07.085635+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/3ASQZWXNRC573EK4NQBXC27LTD","json":"https://pith.science/pith/3ASQZWXNRC573EK4NQBXC27LTD.json","graph_json":"https://pith.science/api/pith-number/3ASQZWXNRC573EK4NQBXC27LTD/graph.json","events_json":"https://pith.science/api/pith-number/3ASQZWXNRC573EK4NQBXC27LTD/events.json","paper":"https://pith.science/paper/3ASQZWXN"},"agent_actions":{"view_html":"https://pith.science/pith/3ASQZWXNRC573EK4NQBXC27LTD","download_json":"https://pith.science/pith/3ASQZWXNRC573EK4NQBXC27LTD.json","view_paper":"https://pith.science/paper/3ASQZWXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.00613&json=true","fetch_graph":"https://pith.science/api/pith-number/3ASQZWXNRC573EK4NQBXC27LTD/graph.json","fetch_events":"https://pith.science/api/pith-number/3ASQZWXNRC573EK4NQBXC27LTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ASQZWXNRC573EK4NQBXC27LTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ASQZWXNRC573EK4NQBXC27LTD/action/storage_attestation","attest_author":"https://pith.science/pith/3ASQZWXNRC573EK4NQBXC27LTD/action/author_attestation","sign_citation":"https://pith.science/pith/3ASQZWXNRC573EK4NQBXC27LTD/action/citation_signature","submit_replication":"https://pith.science/pith/3ASQZWXNRC573EK4NQBXC27LTD/action/replication_record"}},"created_at":"2026-05-17T23:54:52.674464+00:00","updated_at":"2026-05-17T23:54:52.674464+00:00"}