{"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/unsupervised-multilingual-dense-retrieval-via","title":"Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labeling","arxiv_id":"2403.03516","date":"2024-03-06","proceeding":null,"authors":["Chao-Wei Huang","Chen-An Li","Tsu-Yuan Hsu","Chen-Yu Hsu","Yun-Nung Chen"],"abstract":"Dense retrieval methods have demonstrated promising performance in multilingual information retrieval, where queries and documents can be in different languages. However, dense retrievers typically require a substantial amount of paired data, which poses even greater challenges in multilingual scenarios. This paper introduces UMR, an Unsupervised Multilingual dense Retriever trained without any paired data. Our approach leverages the sequence likelihood estimation capabilities of multilingual language models to acquire pseudo labels for training dense retrievers. We propose a two-stage framework which iteratively improves the performance of multilingual dense retrievers. Experimental results on two benchmark datasets show that UMR outperforms supervised baselines, showcasing the potential of training multilingual retrievers without paired data, thereby enhancing their practicality. Our source code, data, and models are publicly available at https://github.com/MiuLab/UMR","url_abs":"https://arxiv.org/abs/2403.03516v1","url_pdf":"https://arxiv.org/pdf/2403.03516v1.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":"unsupervised-multilingual-dense-retrieval-via","repo_url":"https://github.com/miulab/umr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.03516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03516"}},"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/MiuLab/UMR","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"ran_fixture":1,"ran":6,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":13,"ran":11,"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":13,"samples":[{"code_sha256_prefix":"928414780ee23e45","entry":"dot_product_scores","repo":"MiuLab/UMR","repo_kind":"official","path":"dpr/models/biencoder.py","file_url":"https://github.com/MiuLab/UMR/blob/HEAD/dpr/models/biencoder.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"928414780ee23e45"}},{"code_sha256_prefix":"1df81ea9d2da7b70","entry":"compute_loss","repo":"MiuLab/UMR","repo_kind":"official","path":"dpr/models/reader.py","file_url":"https://github.com/MiuLab/UMR/blob/HEAD/dpr/models/reader.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1df81ea9d2da7b70"}},{"code_sha256_prefix":"4c7d079ed8d8dd58","entry":"cosine_scores","repo":"MiuLab/UMR","repo_kind":"official","path":"dpr/models/biencoder.py","file_url":"https://github.com/MiuLab/UMR/blob/HEAD/dpr/models/biencoder.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4c7d079ed8d8dd58"}},{"code_sha256_prefix":"7a6c74fdb61f4457","entry":"dot_product_scores_per_question","repo":"MiuLab/UMR","repo_kind":"official","path":"dpr/models/biencoder.py","file_url":"https://github.com/MiuLab/UMR/blob/HEAD/dpr/models/biencoder.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":"7a6c74fdb61f4457"}},{"code_sha256_prefix":"538cfaef12b25b54","entry":"get_encoder_params_state","repo":"MiuLab/UMR","repo_kind":"official","path":"dpr/options.py","file_url":"https://github.com/MiuLab/UMR/blob/HEAD/dpr/options.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":"538cfaef12b25b54"}},{"code_sha256_prefix":"58e693877d7ab1d4","entry":"get_openqa_dataset","repo":"MiuLab/UMR","repo_kind":"official","path":"openqa_dataset.py","file_url":"https://github.com/MiuLab/UMR/blob/HEAD/openqa_dataset.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":"58e693877d7ab1d4"}},{"code_sha256_prefix":"3e65fdbefb42a546","entry":"load_passages","repo":"MiuLab/UMR","repo_kind":"official","path":"dense_retriever.py","file_url":"https://github.com/MiuLab/UMR/blob/HEAD/dense_retriever.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3e65fdbefb42a546"}},{"code_sha256_prefix":"f754a83bdbe3d5ed","entry":"move_to_cuda","repo":"MiuLab/UMR","repo_kind":"official","path":"dpr/utils/model_utils.py","file_url":"https://github.com/MiuLab/UMR/blob/HEAD/dpr/utils/model_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":"f754a83bdbe3d5ed"}},{"code_sha256_prefix":"5ef6dc01ca2773cb","entry":"move_to_device","repo":"MiuLab/UMR","repo_kind":"official","path":"dpr/utils/model_utils.py","file_url":"https://github.com/MiuLab/UMR/blob/HEAD/dpr/utils/model_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":"5ef6dc01ca2773cb"}},{"code_sha256_prefix":"4d5516637b50f1ad","entry":"no_op_collate","repo":"MiuLab/UMR","repo_kind":"official","path":"generate_dense_embeddings.py","file_url":"https://github.com/MiuLab/UMR/blob/HEAD/generate_dense_embeddings.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4d5516637b50f1ad"}},{"code_sha256_prefix":"afbf1cc123bbd716","entry":"setup_for_distributed_mode","repo":"MiuLab/UMR","repo_kind":"official","path":"dpr/utils/model_utils.py","file_url":"https://github.com/MiuLab/UMR/blob/HEAD/dpr/utils/model_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":"afbf1cc123bbd716"}},{"code_sha256_prefix":"f23a821208a8fdba","entry":"compute_loss_yes_no","repo":"MiuLab/UMR","repo_kind":"official","path":"dpr/models/reader.py","file_url":"https://github.com/MiuLab/UMR/blob/HEAD/dpr/models/reader.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":"f23a821208a8fdba"}},{"code_sha256_prefix":"e44c1974fb9752d3","entry":"set_encoder_params_from_state","repo":"MiuLab/UMR","repo_kind":"official","path":"dpr/options.py","file_url":"https://github.com/MiuLab/UMR/blob/HEAD/dpr/options.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":"e44c1974fb9752d3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}