{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VG5QQDUGPGGFP6XNFVK57MONR7","short_pith_number":"pith:VG5QQDUG","schema_version":"1.0","canonical_sha256":"a9bb080e86798c57faed2d55dfb1cd8fc8bd9ae009716b23df85e7eeaedab535","source":{"kind":"arxiv","id":"2501.19314","version":1},"attestation_state":"computed","paper":{"title":"An Efficient Approach for Machine Translation on Low-resource Languages: A Case Study in Vietnamese-Chinese","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nguyen Anh Tu, Nguyen Minh Tri, Tran Ngoc Son","submitted_at":"2025-01-31T17:11:45Z","abstract_excerpt":"Despite the rise of recent neural networks in machine translation, those networks do not work well if the training data is insufficient. In this paper, we proposed an approach for machine translation in low-resource languages such as Vietnamese-Chinese. Our proposed method leveraged the power of the multilingual pre-trained language model (mBART) and both Vietnamese and Chinese monolingual corpus. Firstly, we built an early bird machine translation model using the bilingual training dataset. Secondly, we used TF-IDF technique to select sentences from the monolingual corpus which are the most r"},"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":"2501.19314","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T17:11:45Z","cross_cats_sorted":[],"title_canon_sha256":"9d13f5124107b85313418df1b625289db06ae6bf7c0c0f53745e5042a9aedcec","abstract_canon_sha256":"9588dfcc983ae7e5541fb05334a9e21705699bb559d7104f30e37a4c19f4c4b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:59.531801Z","signature_b64":"lllw8pb253doBRIkHQh2+oAMfT+tY9ugveW6pc+oQdb1eMNca1A21hIPkszhcXmWi0LQF5g/ZXU2h+vo3QSBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9bb080e86798c57faed2d55dfb1cd8fc8bd9ae009716b23df85e7eeaedab535","last_reissued_at":"2026-07-05T10:07:59.531404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:59.531404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Efficient Approach for Machine Translation on Low-resource Languages: A Case Study in Vietnamese-Chinese","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nguyen Anh Tu, Nguyen Minh Tri, Tran Ngoc Son","submitted_at":"2025-01-31T17:11:45Z","abstract_excerpt":"Despite the rise of recent neural networks in machine translation, those networks do not work well if the training data is insufficient. In this paper, we proposed an approach for machine translation in low-resource languages such as Vietnamese-Chinese. Our proposed method leveraged the power of the multilingual pre-trained language model (mBART) and both Vietnamese and Chinese monolingual corpus. Firstly, we built an early bird machine translation model using the bilingual training dataset. Secondly, we used TF-IDF technique to select sentences from the monolingual corpus which are the most r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19314","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/2501.19314/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":"2501.19314","created_at":"2026-07-05T10:07:59.531455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.19314v1","created_at":"2026-07-05T10:07:59.531455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19314","created_at":"2026-07-05T10:07:59.531455+00:00"},{"alias_kind":"pith_short_12","alias_value":"VG5QQDUGPGGF","created_at":"2026-07-05T10:07:59.531455+00:00"},{"alias_kind":"pith_short_16","alias_value":"VG5QQDUGPGGFP6XN","created_at":"2026-07-05T10:07:59.531455+00:00"},{"alias_kind":"pith_short_8","alias_value":"VG5QQDUG","created_at":"2026-07-05T10:07:59.531455+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18389","citing_title":"Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VG5QQDUGPGGFP6XNFVK57MONR7","json":"https://pith.science/pith/VG5QQDUGPGGFP6XNFVK57MONR7.json","graph_json":"https://pith.science/api/pith-number/VG5QQDUGPGGFP6XNFVK57MONR7/graph.json","events_json":"https://pith.science/api/pith-number/VG5QQDUGPGGFP6XNFVK57MONR7/events.json","paper":"https://pith.science/paper/VG5QQDUG"},"agent_actions":{"view_html":"https://pith.science/pith/VG5QQDUGPGGFP6XNFVK57MONR7","download_json":"https://pith.science/pith/VG5QQDUGPGGFP6XNFVK57MONR7.json","view_paper":"https://pith.science/paper/VG5QQDUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.19314&json=true","fetch_graph":"https://pith.science/api/pith-number/VG5QQDUGPGGFP6XNFVK57MONR7/graph.json","fetch_events":"https://pith.science/api/pith-number/VG5QQDUGPGGFP6XNFVK57MONR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VG5QQDUGPGGFP6XNFVK57MONR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VG5QQDUGPGGFP6XNFVK57MONR7/action/storage_attestation","attest_author":"https://pith.science/pith/VG5QQDUGPGGFP6XNFVK57MONR7/action/author_attestation","sign_citation":"https://pith.science/pith/VG5QQDUGPGGFP6XNFVK57MONR7/action/citation_signature","submit_replication":"https://pith.science/pith/VG5QQDUGPGGFP6XNFVK57MONR7/action/replication_record"}},"created_at":"2026-07-05T10:07:59.531455+00:00","updated_at":"2026-07-05T10:07:59.531455+00:00"}