{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/towards-cross-cultural-machine-translation","title":"Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs","arxiv_id":"2410.14057","date":"2024-10-17","proceeding":null,"authors":["Simone Conia","Daniel Lee","Min Li","Umar Farooq Minhas","Saloni Potdar","Yunyao Li"],"abstract":"Translating text that contains entity names is a challenging task, as cultural-related references can vary significantly across languages. These variations may also be caused by transcreation, an adaptation process that entails more than transliteration and word-for-word translation. In this paper, we address the problem of cross-cultural translation on two fronts: (i) we introduce XC-Translate, the first large-scale, manually-created benchmark for machine translation that focuses on text that contains potentially culturally-nuanced entity names, and (ii) we propose KG-MT, a novel end-to-end method to integrate information from a multilingual knowledge graph into a neural machine translation model by leveraging a dense retrieval mechanism. Our experiments and analyses show that current machine translation systems and large language models still struggle to translate texts containing entity names, whereas KG-MT outperforms state-of-the-art approaches by a large margin, obtaining a 129% and 62% relative improvement compared to NLLB-200 and GPT-4, respectively.","url_abs":"https://arxiv.org/abs/2410.14057v1","url_pdf":"https://arxiv.org/pdf/2410.14057v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"transliteration","task_name":"Transliteration"},{"task_slug":"word-translation","task_name":"Word Translation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.14057","atlas_url":"https://app.syntology.ai/?focus=2410.14057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14057"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/apple/ml-kg-mt","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":5},"by_repo_kind":{"found_in_text":{"samples":5,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":5,"samples":[{"code_sha256_prefix":"ad28e1773da396f9","entry":"compute_entity_name_translation_accuracy","repo":"apple/ml-kg-mt","repo_kind":"found_in_text","path":"src/evaluation/evaluate.py","file_url":"https://github.com/apple/ml-kg-mt/blob/HEAD/src/evaluation/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ad28e1773da396f9"}},{"code_sha256_prefix":"7a3c11758cb7fd77","entry":"get_wikidata_ids","repo":"apple/ml-kg-mt","repo_kind":"found_in_text","path":"src/model/kgmt.py","file_url":"https://github.com/apple/ml-kg-mt/blob/HEAD/src/model/kgmt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7a3c11758cb7fd77"}},{"code_sha256_prefix":"d0c8d3c6b19ef488","entry":"get_wikidata_info","repo":"apple/ml-kg-mt","repo_kind":"found_in_text","path":"src/model/kgmt.py","file_url":"https://github.com/apple/ml-kg-mt/blob/HEAD/src/model/kgmt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d0c8d3c6b19ef488"}},{"code_sha256_prefix":"aaca1dfcefe36000","entry":"load_predictions","repo":"apple/ml-kg-mt","repo_kind":"found_in_text","path":"src/evaluation/evaluate.py","file_url":"https://github.com/apple/ml-kg-mt/blob/HEAD/src/evaluation/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"aaca1dfcefe36000"}},{"code_sha256_prefix":"bcb0b72f4ed549ef","entry":"load_references","repo":"apple/ml-kg-mt","repo_kind":"found_in_text","path":"src/evaluation/evaluate.py","file_url":"https://github.com/apple/ml-kg-mt/blob/HEAD/src/evaluation/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bcb0b72f4ed549ef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}