{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:DNUHTG2HUVK7YIIN5GGG7BIGCJ","short_pith_number":"pith:DNUHTG2H","schema_version":"1.0","canonical_sha256":"1b68799b47a555fc210de98c6f850612506ad7ef26510f7830913f23be0011bb","source":{"kind":"arxiv","id":"1508.04257","version":2},"attestation_state":"computed","paper":{"title":"Learning Meta-Embeddings by Using Ensembles of Embedding Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Wenpeng Yin","submitted_at":"2015-08-18T09:29:22Z","abstract_excerpt":"Word embeddings -- distributed representations of words -- in deep learning are beneficial for many tasks in natural language processing (NLP). However, different embedding sets vary greatly in quality and characteristics of the captured semantics. Instead of relying on a more advanced algorithm for embedding learning, this paper proposes an ensemble approach of combining different public embedding sets with the aim of learning meta-embeddings. Experiments on word similarity and analogy tasks and on part-of-speech tagging show better performance of meta-embeddings compared to individual embedd"},"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":"1508.04257","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-18T09:29:22Z","cross_cats_sorted":[],"title_canon_sha256":"1405c4d1073db9a1e3b0dc7ac3fd765eb6669c71938d2b7e69d136f7cacbe1a4","abstract_canon_sha256":"18ff2cf3a8138dc90f80e956d5aed03698cc547d143cf97d9a5e9707b7473592"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:37.991260Z","signature_b64":"jOPUUgiD1jIE0ucAjfBO1Z+Qt58XtfvBqIIky+MonfhGiOWC0wsaTmmT93EQn+o2jK9yUylWed2AeEI6YgGtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b68799b47a555fc210de98c6f850612506ad7ef26510f7830913f23be0011bb","last_reissued_at":"2026-05-18T01:23:37.990534Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:37.990534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Meta-Embeddings by Using Ensembles of Embedding Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Wenpeng Yin","submitted_at":"2015-08-18T09:29:22Z","abstract_excerpt":"Word embeddings -- distributed representations of words -- in deep learning are beneficial for many tasks in natural language processing (NLP). However, different embedding sets vary greatly in quality and characteristics of the captured semantics. Instead of relying on a more advanced algorithm for embedding learning, this paper proposes an ensemble approach of combining different public embedding sets with the aim of learning meta-embeddings. Experiments on word similarity and analogy tasks and on part-of-speech tagging show better performance of meta-embeddings compared to individual embedd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.04257","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":"1508.04257","created_at":"2026-05-18T01:23:37.990658+00:00"},{"alias_kind":"arxiv_version","alias_value":"1508.04257v2","created_at":"2026-05-18T01:23:37.990658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.04257","created_at":"2026-05-18T01:23:37.990658+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNUHTG2HUVK7","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNUHTG2HUVK7YIIN","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNUHTG2H","created_at":"2026-05-18T12:29:17.054201+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/DNUHTG2HUVK7YIIN5GGG7BIGCJ","json":"https://pith.science/pith/DNUHTG2HUVK7YIIN5GGG7BIGCJ.json","graph_json":"https://pith.science/api/pith-number/DNUHTG2HUVK7YIIN5GGG7BIGCJ/graph.json","events_json":"https://pith.science/api/pith-number/DNUHTG2HUVK7YIIN5GGG7BIGCJ/events.json","paper":"https://pith.science/paper/DNUHTG2H"},"agent_actions":{"view_html":"https://pith.science/pith/DNUHTG2HUVK7YIIN5GGG7BIGCJ","download_json":"https://pith.science/pith/DNUHTG2HUVK7YIIN5GGG7BIGCJ.json","view_paper":"https://pith.science/paper/DNUHTG2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1508.04257&json=true","fetch_graph":"https://pith.science/api/pith-number/DNUHTG2HUVK7YIIN5GGG7BIGCJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DNUHTG2HUVK7YIIN5GGG7BIGCJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNUHTG2HUVK7YIIN5GGG7BIGCJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNUHTG2HUVK7YIIN5GGG7BIGCJ/action/storage_attestation","attest_author":"https://pith.science/pith/DNUHTG2HUVK7YIIN5GGG7BIGCJ/action/author_attestation","sign_citation":"https://pith.science/pith/DNUHTG2HUVK7YIIN5GGG7BIGCJ/action/citation_signature","submit_replication":"https://pith.science/pith/DNUHTG2HUVK7YIIN5GGG7BIGCJ/action/replication_record"}},"created_at":"2026-05-18T01:23:37.990658+00:00","updated_at":"2026-05-18T01:23:37.990658+00:00"}