{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GZCWEVMY4JASX4JLD55FF3SPFJ","short_pith_number":"pith:GZCWEVMY","schema_version":"1.0","canonical_sha256":"3645625598e2412bf12b1f7a52ee4f2a67200385afe8c697d88830b5d6b9e506","source":{"kind":"arxiv","id":"2004.02071","version":1},"attestation_state":"computed","paper":{"title":"Incorporating Bilingual Dictionaries for Low Resource Semi-Supervised Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mihir Kale, Sreyashi Nag, Swapnil Singhavi, Varun Lakshminarasimhan","submitted_at":"2020-04-05T02:14:14Z","abstract_excerpt":"We explore ways of incorporating bilingual dictionaries to enable semi-supervised neural machine translation. Conventional back-translation methods have shown success in leveraging target side monolingual data. However, since the quality of back-translation models is tied to the size of the available parallel corpora, this could adversely impact the synthetically generated sentences in a low resource setting. We propose a simple data augmentation technique to address both this shortcoming. We incorporate widely available bilingual dictionaries that yield word-by-word translations to generate s"},"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":"2004.02071","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T02:14:14Z","cross_cats_sorted":[],"title_canon_sha256":"65850ca2105227f4245337b6fb0902d9229065f52e5a164584d12f542cd13c88","abstract_canon_sha256":"bfef49cf9a96a225abfd3c3e47601021fcf15831518d186d3ff8daff46e29d95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:55.679403Z","signature_b64":"ApPcoh1QyZhmtWWKW+YYTkqUO/XhJfty2uYB5Iyp0lLW9yDSnEfAqETbtCZKdcjx+C6YX/CulgIM/KLsdQiUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3645625598e2412bf12b1f7a52ee4f2a67200385afe8c697d88830b5d6b9e506","last_reissued_at":"2026-07-05T00:52:55.678970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:55.678970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incorporating Bilingual Dictionaries for Low Resource Semi-Supervised Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mihir Kale, Sreyashi Nag, Swapnil Singhavi, Varun Lakshminarasimhan","submitted_at":"2020-04-05T02:14:14Z","abstract_excerpt":"We explore ways of incorporating bilingual dictionaries to enable semi-supervised neural machine translation. Conventional back-translation methods have shown success in leveraging target side monolingual data. However, since the quality of back-translation models is tied to the size of the available parallel corpora, this could adversely impact the synthetically generated sentences in a low resource setting. We propose a simple data augmentation technique to address both this shortcoming. We incorporate widely available bilingual dictionaries that yield word-by-word translations to generate s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02071","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.02071/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2004.02071","created_at":"2026-07-05T00:52:55.679031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.02071v1","created_at":"2026-07-05T00:52:55.679031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02071","created_at":"2026-07-05T00:52:55.679031+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZCWEVMY4JAS","created_at":"2026-07-05T00:52:55.679031+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZCWEVMY4JASX4JL","created_at":"2026-07-05T00:52:55.679031+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZCWEVMY","created_at":"2026-07-05T00:52:55.679031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15069","citing_title":"In-Domain African Languages Translation Using LLMs and Multi-armed Bandits","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZCWEVMY4JASX4JLD55FF3SPFJ","json":"https://pith.science/pith/GZCWEVMY4JASX4JLD55FF3SPFJ.json","graph_json":"https://pith.science/api/pith-number/GZCWEVMY4JASX4JLD55FF3SPFJ/graph.json","events_json":"https://pith.science/api/pith-number/GZCWEVMY4JASX4JLD55FF3SPFJ/events.json","paper":"https://pith.science/paper/GZCWEVMY"},"agent_actions":{"view_html":"https://pith.science/pith/GZCWEVMY4JASX4JLD55FF3SPFJ","download_json":"https://pith.science/pith/GZCWEVMY4JASX4JLD55FF3SPFJ.json","view_paper":"https://pith.science/paper/GZCWEVMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.02071&json=true","fetch_graph":"https://pith.science/api/pith-number/GZCWEVMY4JASX4JLD55FF3SPFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GZCWEVMY4JASX4JLD55FF3SPFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZCWEVMY4JASX4JLD55FF3SPFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZCWEVMY4JASX4JLD55FF3SPFJ/action/storage_attestation","attest_author":"https://pith.science/pith/GZCWEVMY4JASX4JLD55FF3SPFJ/action/author_attestation","sign_citation":"https://pith.science/pith/GZCWEVMY4JASX4JLD55FF3SPFJ/action/citation_signature","submit_replication":"https://pith.science/pith/GZCWEVMY4JASX4JLD55FF3SPFJ/action/replication_record"}},"created_at":"2026-07-05T00:52:55.679031+00:00","updated_at":"2026-07-05T00:52:55.679031+00:00"}