{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FAGLIR5LRFEN6S6QDKXJHTQHEJ","short_pith_number":"pith:FAGLIR5L","schema_version":"1.0","canonical_sha256":"280cb447ab8948df4bd01aae93ce072248e4a9f692653398813ed6453ca0f3c6","source":{"kind":"arxiv","id":"1704.03471","version":3},"attestation_state":"computed","paper":{"title":"What do Neural Machine Translation Models Learn about Morphology?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fahim Dalvi, Hassan Sajjad, James Glass, Nadir Durrani, Yonatan Belinkov","submitted_at":"2017-04-11T18:01:07Z","abstract_excerpt":"Neural machine translation (MT) models obtain state-of-the-art performance while maintaining a simple, end-to-end architecture. However, little is known about what these models learn about source and target languages during the training process. In this work, we analyze the representations learned by neural MT models at various levels of granularity and empirically evaluate the quality of the representations for learning morphology through extrinsic part-of-speech and morphological tagging tasks. We conduct a thorough investigation along several parameters: word-based vs. character-based repre"},"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":"1704.03471","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-11T18:01:07Z","cross_cats_sorted":[],"title_canon_sha256":"1651a2e029ec7ab93348524aa040995d48dca5921d8ab122e7aa94c0967ef4da","abstract_canon_sha256":"200abfb3af1da551730364dfe1a5ad1e9d603c66198677891d3fd820aa298f50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:45.792051Z","signature_b64":"gcZ93t7mwwCtWJ+iyHrcasZJfZqkF80sWLR+KemVbq8sKus+KOPvTrtvZmtnAC3EnmGXAS77uKMHhGtfU5otCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"280cb447ab8948df4bd01aae93ce072248e4a9f692653398813ed6453ca0f3c6","last_reissued_at":"2026-05-18T00:02:45.791543Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:45.791543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What do Neural Machine Translation Models Learn about Morphology?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fahim Dalvi, Hassan Sajjad, James Glass, Nadir Durrani, Yonatan Belinkov","submitted_at":"2017-04-11T18:01:07Z","abstract_excerpt":"Neural machine translation (MT) models obtain state-of-the-art performance while maintaining a simple, end-to-end architecture. However, little is known about what these models learn about source and target languages during the training process. In this work, we analyze the representations learned by neural MT models at various levels of granularity and empirically evaluate the quality of the representations for learning morphology through extrinsic part-of-speech and morphological tagging tasks. We conduct a thorough investigation along several parameters: word-based vs. character-based repre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03471","kind":"arxiv","version":3},"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":"1704.03471","created_at":"2026-05-18T00:02:45.791610+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.03471v3","created_at":"2026-05-18T00:02:45.791610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03471","created_at":"2026-05-18T00:02:45.791610+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAGLIR5LRFEN","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAGLIR5LRFEN6S6Q","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAGLIR5L","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.12284","citing_title":"Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAGLIR5LRFEN6S6QDKXJHTQHEJ","json":"https://pith.science/pith/FAGLIR5LRFEN6S6QDKXJHTQHEJ.json","graph_json":"https://pith.science/api/pith-number/FAGLIR5LRFEN6S6QDKXJHTQHEJ/graph.json","events_json":"https://pith.science/api/pith-number/FAGLIR5LRFEN6S6QDKXJHTQHEJ/events.json","paper":"https://pith.science/paper/FAGLIR5L"},"agent_actions":{"view_html":"https://pith.science/pith/FAGLIR5LRFEN6S6QDKXJHTQHEJ","download_json":"https://pith.science/pith/FAGLIR5LRFEN6S6QDKXJHTQHEJ.json","view_paper":"https://pith.science/paper/FAGLIR5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.03471&json=true","fetch_graph":"https://pith.science/api/pith-number/FAGLIR5LRFEN6S6QDKXJHTQHEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FAGLIR5LRFEN6S6QDKXJHTQHEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAGLIR5LRFEN6S6QDKXJHTQHEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAGLIR5LRFEN6S6QDKXJHTQHEJ/action/storage_attestation","attest_author":"https://pith.science/pith/FAGLIR5LRFEN6S6QDKXJHTQHEJ/action/author_attestation","sign_citation":"https://pith.science/pith/FAGLIR5LRFEN6S6QDKXJHTQHEJ/action/citation_signature","submit_replication":"https://pith.science/pith/FAGLIR5LRFEN6S6QDKXJHTQHEJ/action/replication_record"}},"created_at":"2026-05-18T00:02:45.791610+00:00","updated_at":"2026-05-18T00:02:45.791610+00:00"}