{"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/miners-multilingual-language-models-as","title":"MINERS: Multilingual Language Models as Semantic Retrievers","arxiv_id":"2406.07424","date":"2024-06-11","proceeding":null,"authors":["Genta Indra Winata","Ruochen Zhang","David Ifeoluwa Adelani"],"abstract":"Words have been represented in a high-dimensional vector space that encodes their semantic similarities, enabling downstream applications such as retrieving synonyms, antonyms, and relevant contexts. However, despite recent advances in multilingual language models (LMs), the effectiveness of these models' representations in semantic retrieval contexts has not been comprehensively explored. To fill this gap, this paper introduces the MINERS, a benchmark designed to evaluate the ability of multilingual LMs in semantic retrieval tasks, including bitext mining and classification via retrieval-augmented contexts. We create a comprehensive framework to assess the robustness of LMs in retrieving samples across over 200 diverse languages, including extremely low-resource languages in challenging cross-lingual and code-switching settings. Our results demonstrate that by solely retrieving semantically similar embeddings yields performance competitive with state-of-the-art approaches, without requiring any fine-tuning.","url_abs":"https://arxiv.org/abs/2406.07424v3","url_pdf":"https://arxiv.org/pdf/2406.07424v3.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":"miners-multilingual-language-models-as","repo_url":"https://github.com/gentaiscool/miners","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"semantic-retrieval","task_name":"Semantic Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.07424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07424"}},"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/gentaiscool/miners","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":9,"unverified":1},"by_repo_kind":{"official":{"samples":10,"ran":9,"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":0,"samples":[{"code_sha256_prefix":"1d233f39e0fd58dd","entry":"argmax","repo":"gentaiscool/miners","repo_kind":"official","path":"icl.py","file_url":"https://github.com/gentaiscool/miners/blob/HEAD/icl.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1d233f39e0fd58dd"}},{"code_sha256_prefix":"5c5225ec7c94e346","entry":"evaluate_bitext_mining","repo":"gentaiscool/miners","repo_kind":"official","path":"bitext.py","file_url":"https://github.com/gentaiscool/miners/blob/HEAD/bitext.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c5225ec7c94e346"}},{"code_sha256_prefix":"4643906af527fdf1","entry":"evaluate_bitext_mining","repo":"gentaiscool/miners","repo_kind":"official","path":"bitext_ensemble.py","file_url":"https://github.com/gentaiscool/miners/blob/HEAD/bitext_ensemble.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4643906af527fdf1"}},{"code_sha256_prefix":"73e0a652d3ec6ca9","entry":"evaluate_classification","repo":"gentaiscool/miners","repo_kind":"official","path":"classification.py","file_url":"https://github.com/gentaiscool/miners/blob/HEAD/classification.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"73e0a652d3ec6ca9"}},{"code_sha256_prefix":"dd6254a6573baa16","entry":"evaluate_classification","repo":"gentaiscool/miners","repo_kind":"official","path":"classification_ensemble.py","file_url":"https://github.com/gentaiscool/miners/blob/HEAD/classification_ensemble.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dd6254a6573baa16"}},{"code_sha256_prefix":"bae8ecac288828c5","entry":"get_cohere_embedding","repo":"gentaiscool/miners","repo_kind":"official","path":"bitext.py","file_url":"https://github.com/gentaiscool/miners/blob/HEAD/bitext.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bae8ecac288828c5"}},{"code_sha256_prefix":"89976ba52f51bd6e","entry":"get_openai_embedding","repo":"gentaiscool/miners","repo_kind":"official","path":"bitext.py","file_url":"https://github.com/gentaiscool/miners/blob/HEAD/bitext.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"89976ba52f51bd6e"}},{"code_sha256_prefix":"80c5aec8fadb2125","entry":"logsumexp","repo":"gentaiscool/miners","repo_kind":"official","path":"icl.py","file_url":"https://github.com/gentaiscool/miners/blob/HEAD/icl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"80c5aec8fadb2125"}},{"code_sha256_prefix":"f15777c5ca784848","entry":"normalize","repo":"gentaiscool/miners","repo_kind":"official","path":"icl.py","file_url":"https://github.com/gentaiscool/miners/blob/HEAD/icl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f15777c5ca784848"}},{"code_sha256_prefix":"a0e1f45f8c77f2ec","entry":"get_tokenized_dataset","repo":"gentaiscool/miners","repo_kind":"official","path":"finetune_baseline.py","file_url":"https://github.com/gentaiscool/miners/blob/HEAD/finetune_baseline.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a0e1f45f8c77f2ec"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}