{"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-phrase-retrieval","title":"Cross-Lingual Phrase Retrieval","arxiv_id":"2204.08887","date":"2022-04-19","proceeding":"ACL 2022 5","authors":["Heqi Zheng","Xiao Zhang","Zewen Chi","Heyan Huang","Tan Yan","Tian Lan","Wei Wei","Xian-Ling Mao"],"abstract":"Cross-lingual retrieval aims to retrieve relevant text across languages. Current methods typically achieve cross-lingual retrieval by learning language-agnostic text representations in word or sentence level. However, how to learn phrase representations for cross-lingual phrase retrieval is still an open problem. In this paper, we propose XPR, a cross-lingual phrase retriever that extracts phrase representations from unlabeled example sentences. Moreover, we create a large-scale cross-lingual phrase retrieval dataset, which contains 65K bilingual phrase pairs and 4.2M example sentences in 8 English-centric language pairs. Experimental results show that XPR outperforms state-of-the-art baselines which utilize word-level or sentence-level representations. XPR also shows impressive zero-shot transferability that enables the model to perform retrieval in an unseen language pair during training. Our dataset, code, and trained models are publicly available at www.github.com/cwszz/XPR/.","url_abs":"https://arxiv.org/abs/2204.08887v1","url_pdf":"https://arxiv.org/pdf/2204.08887v1.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-phrase-retrieval","repo_url":"https://github.com/cwszz/xpr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.08887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08887"}},"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":"deterministic:regex_extraction","url":"https://github.com/artetxem/vecmap","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/cwszz/XPR","reach":null}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":11},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1},"found_in_text":{"samples":10,"ran":1,"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":10,"samples":[{"code_sha256_prefix":"8d9f38849ab72f40","entry":"_get_simclr_projection_head","repo":"cwszz/XPR","repo_kind":"official","path":"DictMatching/moco.py","file_url":"https://github.com/cwszz/XPR/blob/HEAD/DictMatching/moco.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d9f38849ab72f40"}},{"code_sha256_prefix":"f44faa56f13d969d","entry":"read","repo":"artetxem/vecmap","repo_kind":"found_in_text","path":"map_embeddings.py","file_url":"https://github.com/artetxem/vecmap/blob/HEAD/map_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f44faa56f13d969d"}},{"code_sha256_prefix":"24c29bb22ce10a95","entry":"BackBone_Model","repo":"cwszz/XPR","repo_kind":"official","path":"DictMatching/moco.py","file_url":"https://github.com/cwszz/XPR/blob/HEAD/DictMatching/moco.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24c29bb22ce10a95"}},{"code_sha256_prefix":"3a932bc84ba92ef4","entry":"MoCo","repo":"cwszz/XPR","repo_kind":"official","path":"DictMatching/moco.py","file_url":"https://github.com/cwszz/XPR/blob/HEAD/DictMatching/moco.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a932bc84ba92ef4"}},{"code_sha256_prefix":"777b8ff7b13f247e","entry":"dropout","repo":"artetxem/vecmap","repo_kind":"found_in_text","path":"map_embeddings.py","file_url":"https://github.com/artetxem/vecmap/blob/HEAD/map_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"777b8ff7b13f247e"}},{"code_sha256_prefix":"aff64d3f5d3d4bd0","entry":"length_normalize","repo":"artetxem/vecmap","repo_kind":"found_in_text","path":"map_embeddings.py","file_url":"https://github.com/artetxem/vecmap/blob/HEAD/map_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"aff64d3f5d3d4bd0"}},{"code_sha256_prefix":"06fb2237db53bafd","entry":"length_normalize_dimensionwise","repo":"artetxem/vecmap","repo_kind":"found_in_text","path":"map_embeddings.py","file_url":"https://github.com/artetxem/vecmap/blob/HEAD/map_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"06fb2237db53bafd"}},{"code_sha256_prefix":"b176513812f649dc","entry":"main","repo":"artetxem/vecmap","repo_kind":"found_in_text","path":"map_embeddings.py","file_url":"https://github.com/artetxem/vecmap/blob/HEAD/map_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b176513812f649dc"}},{"code_sha256_prefix":"c68b12b7ffa541c6","entry":"mean_center","repo":"artetxem/vecmap","repo_kind":"found_in_text","path":"map_embeddings.py","file_url":"https://github.com/artetxem/vecmap/blob/HEAD/map_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"c68b12b7ffa541c6"}},{"code_sha256_prefix":"978712ab1be88991","entry":"mean_center_embeddingwise","repo":"artetxem/vecmap","repo_kind":"found_in_text","path":"map_embeddings.py","file_url":"https://github.com/artetxem/vecmap/blob/HEAD/map_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"978712ab1be88991"}},{"code_sha256_prefix":"90527cc6977ea1f7","entry":"normalize","repo":"artetxem/vecmap","repo_kind":"found_in_text","path":"map_embeddings.py","file_url":"https://github.com/artetxem/vecmap/blob/HEAD/map_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"90527cc6977ea1f7"}},{"code_sha256_prefix":"37c56ac779d6c55d","entry":"topk_mean","repo":"artetxem/vecmap","repo_kind":"found_in_text","path":"map_embeddings.py","file_url":"https://github.com/artetxem/vecmap/blob/HEAD/map_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"37c56ac779d6c55d"}},{"code_sha256_prefix":"262dc75bd09fc6b1","entry":"write","repo":"artetxem/vecmap","repo_kind":"found_in_text","path":"map_embeddings.py","file_url":"https://github.com/artetxem/vecmap/blob/HEAD/map_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"262dc75bd09fc6b1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}