{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SRQZSRVVJWQL62EPN5XXLIQ652","short_pith_number":"pith:SRQZSRVV","schema_version":"1.0","canonical_sha256":"94619946b54da0bf688f6f6f75a21eee97ba4746f7f9015c1673e6a19efd9a9d","source":{"kind":"arxiv","id":"1903.09878","version":2},"attestation_state":"computed","paper":{"title":"Expanding the Text Classification Toolbox with Cross-Lingual Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andreea Hossmann, Claudiu Musat, Meryem M'hamdi, Michael Baeriswyl, Robert West","submitted_at":"2019-03-23T20:25:40Z","abstract_excerpt":"Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. This is creating a new version of the digital divide: the artificial intelligence (AI) divide. Transfer-based approaches, such as Cross-Lingual Text Classification (CLTC) - the task of categorizing texts written in different languages into a common taxonomy, are a promising solution to the emerging AI divide. Recent work on CLTC has focused on demonstrating the benefits of using bilingual word embeddings as features, "},"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":"1903.09878","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-23T20:25:40Z","cross_cats_sorted":[],"title_canon_sha256":"7e0039d05c9aca50eda0a5399e1417868b6853e35c6b2a35b2a1a1ba83c012c1","abstract_canon_sha256":"4d944844487835093c763e8e52919685cd980d60983586952b98537276de258e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:04.320036Z","signature_b64":"GJhfOXLseIW8q1qNbTxZ54OFRbTKFtwpcqWfomvUpjHBw77lPuCGnqS4DIa0vQQuweFh2WW7AhkAZ+vPmpYJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94619946b54da0bf688f6f6f75a21eee97ba4746f7f9015c1673e6a19efd9a9d","last_reissued_at":"2026-05-17T23:50:04.319593Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:04.319593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expanding the Text Classification Toolbox with Cross-Lingual Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andreea Hossmann, Claudiu Musat, Meryem M'hamdi, Michael Baeriswyl, Robert West","submitted_at":"2019-03-23T20:25:40Z","abstract_excerpt":"Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. This is creating a new version of the digital divide: the artificial intelligence (AI) divide. Transfer-based approaches, such as Cross-Lingual Text Classification (CLTC) - the task of categorizing texts written in different languages into a common taxonomy, are a promising solution to the emerging AI divide. Recent work on CLTC has focused on demonstrating the benefits of using bilingual word embeddings as features, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09878","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":"1903.09878","created_at":"2026-05-17T23:50:04.319658+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.09878v2","created_at":"2026-05-17T23:50:04.319658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09878","created_at":"2026-05-17T23:50:04.319658+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRQZSRVVJWQL","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRQZSRVVJWQL62EP","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRQZSRVV","created_at":"2026-05-18T12:33:27.125529+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/SRQZSRVVJWQL62EPN5XXLIQ652","json":"https://pith.science/pith/SRQZSRVVJWQL62EPN5XXLIQ652.json","graph_json":"https://pith.science/api/pith-number/SRQZSRVVJWQL62EPN5XXLIQ652/graph.json","events_json":"https://pith.science/api/pith-number/SRQZSRVVJWQL62EPN5XXLIQ652/events.json","paper":"https://pith.science/paper/SRQZSRVV"},"agent_actions":{"view_html":"https://pith.science/pith/SRQZSRVVJWQL62EPN5XXLIQ652","download_json":"https://pith.science/pith/SRQZSRVVJWQL62EPN5XXLIQ652.json","view_paper":"https://pith.science/paper/SRQZSRVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.09878&json=true","fetch_graph":"https://pith.science/api/pith-number/SRQZSRVVJWQL62EPN5XXLIQ652/graph.json","fetch_events":"https://pith.science/api/pith-number/SRQZSRVVJWQL62EPN5XXLIQ652/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRQZSRVVJWQL62EPN5XXLIQ652/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRQZSRVVJWQL62EPN5XXLIQ652/action/storage_attestation","attest_author":"https://pith.science/pith/SRQZSRVVJWQL62EPN5XXLIQ652/action/author_attestation","sign_citation":"https://pith.science/pith/SRQZSRVVJWQL62EPN5XXLIQ652/action/citation_signature","submit_replication":"https://pith.science/pith/SRQZSRVVJWQL62EPN5XXLIQ652/action/replication_record"}},"created_at":"2026-05-17T23:50:04.319658+00:00","updated_at":"2026-05-17T23:50:04.319658+00:00"}