{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VAQRABMYEMR44GG53IZSETJH5U","short_pith_number":"pith:VAQRABMY","schema_version":"1.0","canonical_sha256":"a8211005982323ce18ddda33224d27ed2d921908291f41e867299bb3ff8e147c","source":{"kind":"arxiv","id":"1808.08437","version":1},"attestation_state":"computed","paper":{"title":"Meta-Learning for Low-Resource Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiatao Gu, Kyunghyun Cho, Victor O.K. Li, Yong Wang, Yun Chen","submitted_at":"2018-08-25T15:10:59Z","abstract_excerpt":"In this paper, we propose to extend the recently introduced model-agnostic meta-learning algorithm (MAML) for low-resource neural machine translation (NMT). We frame low-resource translation as a meta-learning problem, and we learn to adapt to low-resource languages based on multilingual high-resource language tasks. We use the universal lexical representation~\\citep{gu2018universal} to overcome the input-output mismatch across different languages. We evaluate the proposed meta-learning strategy using eighteen European languages (Bg, Cs, Da, De, El, Es, Et, Fr, Hu, It, Lt, Nl, Pl, Pt, Sk, Sl, "},"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":"1808.08437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-25T15:10:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c5f3f23a65642c233dadbedf85946c597559387e6d653e184bd3daf42d801657","abstract_canon_sha256":"563ad3c467495dec2fa5df46d321e96740a5ad439acabb009f069deb81f74e33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:16.490853Z","signature_b64":"QGr+zwXFwoi5HlsmQ8f51XyYS9eVhw7hoY2ehUnuS43Cdf4DcIrr1uHzvj+cCdI74Q8tHK7+96xhjNj0X9C0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8211005982323ce18ddda33224d27ed2d921908291f41e867299bb3ff8e147c","last_reissued_at":"2026-05-18T00:07:16.490207Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:16.490207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning for Low-Resource Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiatao Gu, Kyunghyun Cho, Victor O.K. Li, Yong Wang, Yun Chen","submitted_at":"2018-08-25T15:10:59Z","abstract_excerpt":"In this paper, we propose to extend the recently introduced model-agnostic meta-learning algorithm (MAML) for low-resource neural machine translation (NMT). We frame low-resource translation as a meta-learning problem, and we learn to adapt to low-resource languages based on multilingual high-resource language tasks. We use the universal lexical representation~\\citep{gu2018universal} to overcome the input-output mismatch across different languages. We evaluate the proposed meta-learning strategy using eighteen European languages (Bg, Cs, Da, De, El, Es, Et, Fr, Hu, It, Lt, Nl, Pl, Pt, Sk, Sl, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08437","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":"1808.08437","created_at":"2026-05-18T00:07:16.490300+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.08437v1","created_at":"2026-05-18T00:07:16.490300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08437","created_at":"2026-05-18T00:07:16.490300+00:00"},{"alias_kind":"pith_short_12","alias_value":"VAQRABMYEMR4","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VAQRABMYEMR44GG5","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VAQRABMY","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2005.14165","citing_title":"Language Models are Few-Shot Learners","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VAQRABMYEMR44GG53IZSETJH5U","json":"https://pith.science/pith/VAQRABMYEMR44GG53IZSETJH5U.json","graph_json":"https://pith.science/api/pith-number/VAQRABMYEMR44GG53IZSETJH5U/graph.json","events_json":"https://pith.science/api/pith-number/VAQRABMYEMR44GG53IZSETJH5U/events.json","paper":"https://pith.science/paper/VAQRABMY"},"agent_actions":{"view_html":"https://pith.science/pith/VAQRABMYEMR44GG53IZSETJH5U","download_json":"https://pith.science/pith/VAQRABMYEMR44GG53IZSETJH5U.json","view_paper":"https://pith.science/paper/VAQRABMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.08437&json=true","fetch_graph":"https://pith.science/api/pith-number/VAQRABMYEMR44GG53IZSETJH5U/graph.json","fetch_events":"https://pith.science/api/pith-number/VAQRABMYEMR44GG53IZSETJH5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VAQRABMYEMR44GG53IZSETJH5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VAQRABMYEMR44GG53IZSETJH5U/action/storage_attestation","attest_author":"https://pith.science/pith/VAQRABMYEMR44GG53IZSETJH5U/action/author_attestation","sign_citation":"https://pith.science/pith/VAQRABMYEMR44GG53IZSETJH5U/action/citation_signature","submit_replication":"https://pith.science/pith/VAQRABMYEMR44GG53IZSETJH5U/action/replication_record"}},"created_at":"2026-05-18T00:07:16.490300+00:00","updated_at":"2026-05-18T00:07:16.490300+00:00"}