{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:YEHSMOXW3UUWSBA7N2F76T3ZER","short_pith_number":"pith:YEHSMOXW","schema_version":"1.0","canonical_sha256":"c10f263af6dd2969041f6e8bff4f792451ab3ebe5fc49419a32af54de9f61e06","source":{"kind":"arxiv","id":"1504.06654","version":1},"attestation_state":"computed","paper":{"title":"Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Alexandre Passos, Andrew McCallum, Arvind Neelakantan, Jeevan Shankar","submitted_at":"2015-04-24T22:12:14Z","abstract_excerpt":"There is rising interest in vector-space word embeddings and their use in NLP, especially given recent methods for their fast estimation at very large scale. Nearly all this work, however, assumes a single vector per word type ignoring polysemy and thus jeopardizing their usefulness for downstream tasks. We present an extension to the Skip-gram model that efficiently learns multiple embeddings per word type. It differs from recent related work by jointly performing word sense discrimination and embedding learning, by non-parametrically estimating the number of senses per word type, and by its "},"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":"1504.06654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-04-24T22:12:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"46fc3c2e380a60eb97cdc383d25b07f330c298af729a55e00a7b8a17e414a726","abstract_canon_sha256":"74b13b6d155aed0a403d4fdb7215db60e0318c5354061b8e49b5540e0c90449d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:17:52.861329Z","signature_b64":"k3R0nWQe9rwhR7pRmXWLpVj4YWXQGOpnBeh10yt5/H+l4UNzZL0ynOdF86eI7FaOK4RvAP74TCdwA8bq+PtoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c10f263af6dd2969041f6e8bff4f792451ab3ebe5fc49419a32af54de9f61e06","last_reissued_at":"2026-05-18T02:17:52.860771Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:17:52.860771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Alexandre Passos, Andrew McCallum, Arvind Neelakantan, Jeevan Shankar","submitted_at":"2015-04-24T22:12:14Z","abstract_excerpt":"There is rising interest in vector-space word embeddings and their use in NLP, especially given recent methods for their fast estimation at very large scale. Nearly all this work, however, assumes a single vector per word type ignoring polysemy and thus jeopardizing their usefulness for downstream tasks. We present an extension to the Skip-gram model that efficiently learns multiple embeddings per word type. It differs from recent related work by jointly performing word sense discrimination and embedding learning, by non-parametrically estimating the number of senses per word type, and by its "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.06654","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":"1504.06654","created_at":"2026-05-18T02:17:52.860860+00:00"},{"alias_kind":"arxiv_version","alias_value":"1504.06654v1","created_at":"2026-05-18T02:17:52.860860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.06654","created_at":"2026-05-18T02:17:52.860860+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEHSMOXW3UUW","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEHSMOXW3UUWSBA7","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEHSMOXW","created_at":"2026-05-18T12:29:50.041715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2402.19088","citing_title":"Survey in Characterizing Semantic Change","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YEHSMOXW3UUWSBA7N2F76T3ZER","json":"https://pith.science/pith/YEHSMOXW3UUWSBA7N2F76T3ZER.json","graph_json":"https://pith.science/api/pith-number/YEHSMOXW3UUWSBA7N2F76T3ZER/graph.json","events_json":"https://pith.science/api/pith-number/YEHSMOXW3UUWSBA7N2F76T3ZER/events.json","paper":"https://pith.science/paper/YEHSMOXW"},"agent_actions":{"view_html":"https://pith.science/pith/YEHSMOXW3UUWSBA7N2F76T3ZER","download_json":"https://pith.science/pith/YEHSMOXW3UUWSBA7N2F76T3ZER.json","view_paper":"https://pith.science/paper/YEHSMOXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1504.06654&json=true","fetch_graph":"https://pith.science/api/pith-number/YEHSMOXW3UUWSBA7N2F76T3ZER/graph.json","fetch_events":"https://pith.science/api/pith-number/YEHSMOXW3UUWSBA7N2F76T3ZER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEHSMOXW3UUWSBA7N2F76T3ZER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEHSMOXW3UUWSBA7N2F76T3ZER/action/storage_attestation","attest_author":"https://pith.science/pith/YEHSMOXW3UUWSBA7N2F76T3ZER/action/author_attestation","sign_citation":"https://pith.science/pith/YEHSMOXW3UUWSBA7N2F76T3ZER/action/citation_signature","submit_replication":"https://pith.science/pith/YEHSMOXW3UUWSBA7N2F76T3ZER/action/replication_record"}},"created_at":"2026-05-18T02:17:52.860860+00:00","updated_at":"2026-05-18T02:17:52.860860+00:00"}