{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:LH6QJLC6QE3JVVHVPF7EL2ZZW7","short_pith_number":"pith:LH6QJLC6","schema_version":"1.0","canonical_sha256":"59fd04ac5e81369ad4f5797e45eb39b7e5c305adc4937337b88dcf24be17b693","source":{"kind":"arxiv","id":"1402.1454","version":1},"attestation_state":"computed","paper":{"title":"An Autoencoder Approach to Learning Bilingual Word Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Amrita Saha, Balaraman Ravindran, Hugo Larochelle, Mitesh M. Khapra, Sarath Chandar A P, Stanislas Lauly, Vikas Raykar","submitted_at":"2014-02-06T18:53:30Z","abstract_excerpt":"Cross-language learning allows us to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-level alignment of sentences from parallel corpora. In this work we explore the use of autoencoder-based methods for cross-language learning of vectorial word representations that are aligned between two languages, while not relying on word-level alignments. We show that by simply learning to reconstruct the bag-of-words representations of aligned sentences, within and between languages, we can in fact learn high-qual"},"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":"1402.1454","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-02-06T18:53:30Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"1aa48740b6bcda7b168a7efaf84d635bd4f0c55a385252df7bec37c81e465bf9","abstract_canon_sha256":"909e6d2491078a88f0277336ac8ec8c447d0429409a83b2a9d6767be70ec52ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:59:49.071423Z","signature_b64":"84fBqyPy8Hdw+AWLNgKwXQd+ZMYvpTd5wACew4VTfna0jYvHsuBfiMSBCPS4RqS83NAuK8c4MgmHegEUFwqSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59fd04ac5e81369ad4f5797e45eb39b7e5c305adc4937337b88dcf24be17b693","last_reissued_at":"2026-05-18T02:59:49.070430Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:59:49.070430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Autoencoder Approach to Learning Bilingual Word Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Amrita Saha, Balaraman Ravindran, Hugo Larochelle, Mitesh M. Khapra, Sarath Chandar A P, Stanislas Lauly, Vikas Raykar","submitted_at":"2014-02-06T18:53:30Z","abstract_excerpt":"Cross-language learning allows us to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-level alignment of sentences from parallel corpora. In this work we explore the use of autoencoder-based methods for cross-language learning of vectorial word representations that are aligned between two languages, while not relying on word-level alignments. We show that by simply learning to reconstruct the bag-of-words representations of aligned sentences, within and between languages, we can in fact learn high-qual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.1454","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":"1402.1454","created_at":"2026-05-18T02:59:49.070615+00:00"},{"alias_kind":"arxiv_version","alias_value":"1402.1454v1","created_at":"2026-05-18T02:59:49.070615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.1454","created_at":"2026-05-18T02:59:49.070615+00:00"},{"alias_kind":"pith_short_12","alias_value":"LH6QJLC6QE3J","created_at":"2026-05-18T12:28:38.356838+00:00"},{"alias_kind":"pith_short_16","alias_value":"LH6QJLC6QE3JVVHV","created_at":"2026-05-18T12:28:38.356838+00:00"},{"alias_kind":"pith_short_8","alias_value":"LH6QJLC6","created_at":"2026-05-18T12:28:38.356838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1406.1078","citing_title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LH6QJLC6QE3JVVHVPF7EL2ZZW7","json":"https://pith.science/pith/LH6QJLC6QE3JVVHVPF7EL2ZZW7.json","graph_json":"https://pith.science/api/pith-number/LH6QJLC6QE3JVVHVPF7EL2ZZW7/graph.json","events_json":"https://pith.science/api/pith-number/LH6QJLC6QE3JVVHVPF7EL2ZZW7/events.json","paper":"https://pith.science/paper/LH6QJLC6"},"agent_actions":{"view_html":"https://pith.science/pith/LH6QJLC6QE3JVVHVPF7EL2ZZW7","download_json":"https://pith.science/pith/LH6QJLC6QE3JVVHVPF7EL2ZZW7.json","view_paper":"https://pith.science/paper/LH6QJLC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1402.1454&json=true","fetch_graph":"https://pith.science/api/pith-number/LH6QJLC6QE3JVVHVPF7EL2ZZW7/graph.json","fetch_events":"https://pith.science/api/pith-number/LH6QJLC6QE3JVVHVPF7EL2ZZW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LH6QJLC6QE3JVVHVPF7EL2ZZW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LH6QJLC6QE3JVVHVPF7EL2ZZW7/action/storage_attestation","attest_author":"https://pith.science/pith/LH6QJLC6QE3JVVHVPF7EL2ZZW7/action/author_attestation","sign_citation":"https://pith.science/pith/LH6QJLC6QE3JVVHVPF7EL2ZZW7/action/citation_signature","submit_replication":"https://pith.science/pith/LH6QJLC6QE3JVVHVPF7EL2ZZW7/action/replication_record"}},"created_at":"2026-05-18T02:59:49.070615+00:00","updated_at":"2026-05-18T02:59:49.070615+00:00"}