{"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/cross-lingual-contextualized-phrase-retrieval","title":"Cross-lingual Contextualized Phrase Retrieval","arxiv_id":"2403.16820","date":"2024-03-25","proceeding":null,"authors":["Huayang Li","Deng Cai","Zhi Qu","Qu Cui","Hidetaka Kamigaito","Lemao Liu","Taro Watanabe"],"abstract":"Phrase-level dense retrieval has shown many appealing characteristics in downstream NLP tasks by leveraging the fine-grained information that phrases offer. In our work, we propose a new task formulation of dense retrieval, cross-lingual contextualized phrase retrieval, which aims to augment cross-lingual applications by addressing polysemy using context information. However, the lack of specific training data and models are the primary challenges to achieve our goal. As a result, we extract pairs of cross-lingual phrases using word alignment information automatically induced from parallel sentences. Subsequently, we train our Cross-lingual Contextualized Phrase Retriever (CCPR) using contrastive learning, which encourages the hidden representations of phrases with similar contexts and semantics to align closely. Comprehensive experiments on both the cross-lingual phrase retrieval task and a downstream task, i.e, machine translation, demonstrate the effectiveness of CCPR. On the phrase retrieval task, CCPR surpasses baselines by a significant margin, achieving a top-1 accuracy that is at least 13 points higher. When utilizing CCPR to augment the large-language-model-based translator, it achieves average gains of 0.7 and 1.5 in BERTScore for translations from X=>En and vice versa, respectively, on WMT16 dataset. Our code and data are available at \\url{https://github.com/ghrua/ccpr_release}.","url_abs":"https://arxiv.org/abs/2403.16820v2","url_pdf":"https://arxiv.org/pdf/2403.16820v2.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":[{"paper_slug":"cross-lingual-contextualized-phrase-retrieval","repo_url":"https://github.com/ghrua/ccpr_release","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"word-alignment","task_name":"Word Alignment"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.16820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16820"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ghrua/ccpr_release","reach":{"status":"ok"}}],"summary":{"ran":6,"unverified":5},"by_repo_kind":{"official":{"samples":11,"ran":6,"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":11,"samples":[{"code_sha256_prefix":"a2766e878d1e6e6e","entry":"adjust_config","repo":"ghrua/ccpr_release","repo_kind":"official","path":"code/common_utils.py","file_url":"https://github.com/ghrua/ccpr_release/blob/HEAD/code/common_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a2766e878d1e6e6e"}},{"code_sha256_prefix":"00a180bdb40458d6","entry":"decode_labse_with_brackets","repo":"ghrua/ccpr_release","repo_kind":"official","path":"code/project_tools.py","file_url":"https://github.com/ghrua/ccpr_release/blob/HEAD/code/project_tools.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"00a180bdb40458d6"}},{"code_sha256_prefix":"03bb831846ef16e2","entry":"decode_xlmr_with_brackets","repo":"ghrua/ccpr_release","repo_kind":"official","path":"code/project_tools.py","file_url":"https://github.com/ghrua/ccpr_release/blob/HEAD/code/project_tools.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"03bb831846ef16e2"}},{"code_sha256_prefix":"b13d92e90516591c","entry":"escape_xml_chars","repo":"ghrua/ccpr_release","repo_kind":"official","path":"code/eval_retriever.py","file_url":"https://github.com/ghrua/ccpr_release/blob/HEAD/code/eval_retriever.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b13d92e90516591c"}},{"code_sha256_prefix":"78b64014b85a7007","entry":"extract_text_in_quotes","repo":"ghrua/ccpr_release","repo_kind":"official","path":"Platypus/translation.py","file_url":"https://github.com/ghrua/ccpr_release/blob/HEAD/Platypus/translation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"78b64014b85a7007"}},{"code_sha256_prefix":"af6665f5aaaab01e","entry":"override","repo":"ghrua/ccpr_release","repo_kind":"official","path":"code/common_utils.py","file_url":"https://github.com/ghrua/ccpr_release/blob/HEAD/code/common_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"af6665f5aaaab01e"}},{"code_sha256_prefix":"22f43e3b9d994eca","entry":"create_dataloader","repo":"ghrua/ccpr_release","repo_kind":"official","path":"code/dataloader.py","file_url":"https://github.com/ghrua/ccpr_release/blob/HEAD/code/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"22f43e3b9d994eca"}},{"code_sha256_prefix":"cb14e5576d07e35f","entry":"create_model","repo":"ghrua/ccpr_release","repo_kind":"official","path":"code/model.py","file_url":"https://github.com/ghrua/ccpr_release/blob/HEAD/code/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb14e5576d07e35f"}},{"code_sha256_prefix":"3b6550e7e41ca28e","entry":"evaluate","repo":"ghrua/ccpr_release","repo_kind":"official","path":"Platypus/inference.py","file_url":"https://github.com/ghrua/ccpr_release/blob/HEAD/Platypus/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3b6550e7e41ca28e"}},{"code_sha256_prefix":"f256c19f2d48d31b","entry":"get_dataset_class","repo":"ghrua/ccpr_release","repo_kind":"official","path":"code/dataloader.py","file_url":"https://github.com/ghrua/ccpr_release/blob/HEAD/code/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f256c19f2d48d31b"}},{"code_sha256_prefix":"414deab65806558d","entry":"get_model_class","repo":"ghrua/ccpr_release","repo_kind":"official","path":"code/model.py","file_url":"https://github.com/ghrua/ccpr_release/blob/HEAD/code/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"414deab65806558d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}