{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:MYDHGSREBFRSGVFQXI6HQILULN","short_pith_number":"pith:MYDHGSRE","schema_version":"1.0","canonical_sha256":"6606734a2409632354b0ba3c7821745b5236bb234783fe5cc8e70acbe8c63a72","source":{"kind":"arxiv","id":"1706.08160","version":1},"attestation_state":"computed","paper":{"title":"Beyond Bilingual: Multi-sense Word Embeddings using Multilingual Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Kalai, James Zou, Kai-Wei Chang, Matt Taddy, Shyam Upadhyay","submitted_at":"2017-06-25T20:00:54Z","abstract_excerpt":"Word embeddings, which represent a word as a point in a vector space, have become ubiquitous to several NLP tasks. A recent line of work uses bilingual (two languages) corpora to learn a different vector for each sense of a word, by exploiting crosslingual signals to aid sense identification. We present a multi-view Bayesian non-parametric algorithm which improves multi-sense word embeddings by (a) using multilingual (i.e., more than two languages) corpora to significantly improve sense embeddings beyond what one achieves with bilingual information, and (b) uses a principled approach to learn "},"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":"1706.08160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-25T20:00:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e78b8a7f4a8ad33ad8dbd80af2b0c34dcf551ab5ef29b916703bede72088fa96","abstract_canon_sha256":"a48e35559e5fd25939466e70036389f808f6bab91811b0cee00d9beac195551b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:43.372220Z","signature_b64":"ZW2D2ApGL836GyzQy2kp2LOh1od0/SdUCF8oKrDpt1XzvpzP0yvEWUdP+fEIJ2pIIZyHMxDXZhQj3B2jQ6yEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6606734a2409632354b0ba3c7821745b5236bb234783fe5cc8e70acbe8c63a72","last_reissued_at":"2026-05-18T00:41:43.371781Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:43.371781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Bilingual: Multi-sense Word Embeddings using Multilingual Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Kalai, James Zou, Kai-Wei Chang, Matt Taddy, Shyam Upadhyay","submitted_at":"2017-06-25T20:00:54Z","abstract_excerpt":"Word embeddings, which represent a word as a point in a vector space, have become ubiquitous to several NLP tasks. A recent line of work uses bilingual (two languages) corpora to learn a different vector for each sense of a word, by exploiting crosslingual signals to aid sense identification. We present a multi-view Bayesian non-parametric algorithm which improves multi-sense word embeddings by (a) using multilingual (i.e., more than two languages) corpora to significantly improve sense embeddings beyond what one achieves with bilingual information, and (b) uses a principled approach to learn "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.08160","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":"1706.08160","created_at":"2026-05-18T00:41:43.371849+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.08160v1","created_at":"2026-05-18T00:41:43.371849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.08160","created_at":"2026-05-18T00:41:43.371849+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYDHGSREBFRS","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYDHGSREBFRSGVFQ","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYDHGSRE","created_at":"2026-05-18T12:31:31.346846+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/MYDHGSREBFRSGVFQXI6HQILULN","json":"https://pith.science/pith/MYDHGSREBFRSGVFQXI6HQILULN.json","graph_json":"https://pith.science/api/pith-number/MYDHGSREBFRSGVFQXI6HQILULN/graph.json","events_json":"https://pith.science/api/pith-number/MYDHGSREBFRSGVFQXI6HQILULN/events.json","paper":"https://pith.science/paper/MYDHGSRE"},"agent_actions":{"view_html":"https://pith.science/pith/MYDHGSREBFRSGVFQXI6HQILULN","download_json":"https://pith.science/pith/MYDHGSREBFRSGVFQXI6HQILULN.json","view_paper":"https://pith.science/paper/MYDHGSRE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.08160&json=true","fetch_graph":"https://pith.science/api/pith-number/MYDHGSREBFRSGVFQXI6HQILULN/graph.json","fetch_events":"https://pith.science/api/pith-number/MYDHGSREBFRSGVFQXI6HQILULN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYDHGSREBFRSGVFQXI6HQILULN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYDHGSREBFRSGVFQXI6HQILULN/action/storage_attestation","attest_author":"https://pith.science/pith/MYDHGSREBFRSGVFQXI6HQILULN/action/author_attestation","sign_citation":"https://pith.science/pith/MYDHGSREBFRSGVFQXI6HQILULN/action/citation_signature","submit_replication":"https://pith.science/pith/MYDHGSREBFRSGVFQXI6HQILULN/action/replication_record"}},"created_at":"2026-05-18T00:41:43.371849+00:00","updated_at":"2026-05-18T00:41:43.371849+00:00"}