{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CWGTK27RRWXW5PPPVVDTHDKKNP","short_pith_number":"pith:CWGTK27R","schema_version":"1.0","canonical_sha256":"158d356bf18daf6ebdefad47338d4a6bf597a17745c8f9d3ba4b3fba210d41ae","source":{"kind":"arxiv","id":"1808.09500","version":1},"attestation_state":"computed","paper":{"title":"Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditi Chaudhary, Chunting Zhou, David R. Mortensen, Graham Neubig, Jaime G. Carbonell, Lori Levin","submitted_at":"2018-08-28T19:11:20Z","abstract_excerpt":"Much work in Natural Language Processing (NLP) has been for resource-rich languages, making generalization to new, less-resourced languages challenging. We present two approaches for improving generalization to low-resourced languages by adapting continuous word representations using linguistically motivated subword units: phonemes, morphemes and graphemes. Our method requires neither parallel corpora nor bilingual dictionaries and provides a significant gain in performance over previous methods relying on these resources. We demonstrate the effectiveness of our approaches on Named Entity Reco"},"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":"1808.09500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T19:11:20Z","cross_cats_sorted":[],"title_canon_sha256":"dd4f3ed23ec4ec8cb754423e7e743cfe4ceaec00ba66acc2e93f1d4fa9071c08","abstract_canon_sha256":"f17bca156e8b11325ff8756609666b37741ea7b8b3bb7b8444d2bd218e9ebbe6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:55.394252Z","signature_b64":"IYQqWulnsmDG+FssL04VHui2nfFbTXnEEZenv5kP+DJFH7aIR39m5QHNQ47ZIBzYByXPHg8IjVZRicpsRHN4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"158d356bf18daf6ebdefad47338d4a6bf597a17745c8f9d3ba4b3fba210d41ae","last_reissued_at":"2026-05-18T00:06:55.393599Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:55.393599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditi Chaudhary, Chunting Zhou, David R. Mortensen, Graham Neubig, Jaime G. Carbonell, Lori Levin","submitted_at":"2018-08-28T19:11:20Z","abstract_excerpt":"Much work in Natural Language Processing (NLP) has been for resource-rich languages, making generalization to new, less-resourced languages challenging. We present two approaches for improving generalization to low-resourced languages by adapting continuous word representations using linguistically motivated subword units: phonemes, morphemes and graphemes. Our method requires neither parallel corpora nor bilingual dictionaries and provides a significant gain in performance over previous methods relying on these resources. We demonstrate the effectiveness of our approaches on Named Entity Reco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09500","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":"1808.09500","created_at":"2026-05-18T00:06:55.393693+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.09500v1","created_at":"2026-05-18T00:06:55.393693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09500","created_at":"2026-05-18T00:06:55.393693+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWGTK27RRWXW","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWGTK27RRWXW5PPP","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWGTK27R","created_at":"2026-05-18T12:32:19.392346+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/CWGTK27RRWXW5PPPVVDTHDKKNP","json":"https://pith.science/pith/CWGTK27RRWXW5PPPVVDTHDKKNP.json","graph_json":"https://pith.science/api/pith-number/CWGTK27RRWXW5PPPVVDTHDKKNP/graph.json","events_json":"https://pith.science/api/pith-number/CWGTK27RRWXW5PPPVVDTHDKKNP/events.json","paper":"https://pith.science/paper/CWGTK27R"},"agent_actions":{"view_html":"https://pith.science/pith/CWGTK27RRWXW5PPPVVDTHDKKNP","download_json":"https://pith.science/pith/CWGTK27RRWXW5PPPVVDTHDKKNP.json","view_paper":"https://pith.science/paper/CWGTK27R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.09500&json=true","fetch_graph":"https://pith.science/api/pith-number/CWGTK27RRWXW5PPPVVDTHDKKNP/graph.json","fetch_events":"https://pith.science/api/pith-number/CWGTK27RRWXW5PPPVVDTHDKKNP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWGTK27RRWXW5PPPVVDTHDKKNP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWGTK27RRWXW5PPPVVDTHDKKNP/action/storage_attestation","attest_author":"https://pith.science/pith/CWGTK27RRWXW5PPPVVDTHDKKNP/action/author_attestation","sign_citation":"https://pith.science/pith/CWGTK27RRWXW5PPPVVDTHDKKNP/action/citation_signature","submit_replication":"https://pith.science/pith/CWGTK27RRWXW5PPPVVDTHDKKNP/action/replication_record"}},"created_at":"2026-05-18T00:06:55.393693+00:00","updated_at":"2026-05-18T00:06:55.393693+00:00"}