{"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/mkqa-a-linguistically-diverse-benchmark-for","title":"MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering","arxiv_id":"2007.15207","date":"2020-07-30","proceeding":null,"authors":["Shayne Longpre","Yi Lu","Joachim Daiber"],"abstract":"Progress in cross-lingual modeling depends on challenging, realistic, and diverse evaluation sets. We introduce Multilingual Knowledge Questions and Answers (MKQA), an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically diverse languages (260k question-answer pairs in total). Answers are based on a heavily curated, language-independent data representation, making results comparable across languages and independent of language-specific passages. With 26 languages, this dataset supplies the widest range of languages to-date for evaluating question answering. We benchmark a variety of state-of-the-art methods and baselines for generative and extractive question answering, trained on Natural Questions, in zero shot and translation settings. Results indicate this dataset is challenging even in English, but especially in low-resource languages","url_abs":"https://arxiv.org/abs/2007.15207v2","url_pdf":"https://arxiv.org/pdf/2007.15207v2.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":"mkqa-a-linguistically-diverse-benchmark-for","repo_url":"https://github.com/apple/ml-mkqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mkqa-a-linguistically-diverse-benchmark-for","repo_url":"https://github.com/mia-workshop/mia-shared-task-2022","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"extractive-question-answering","task_name":"Extractive Question-Answering"},{"task_slug":"natural-questions","task_name":"Natural Questions"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[{"slug":"mkqa","name":"MKQA","full_name":"Multilingual Knowledge Questions and Answers"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.15207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.15207"}},"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/mia-workshop/mia-shared-task-2022","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/apple/ml-mkqa","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"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":"c095134cad4a24ee","entry":"get_text_metrics","repo":"apple/ml-mkqa","repo_kind":"official","path":"mkqa_eval_util.py","file_url":"https://github.com/apple/ml-mkqa/blob/HEAD/mkqa_eval_util.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":"c095134cad4a24ee"}},{"code_sha256_prefix":"11dc500c3a9d29b0","entry":"map_em_value","repo":"apple/ml-mkqa","repo_kind":"official","path":"mkqa_eval_util.py","file_url":"https://github.com/apple/ml-mkqa/blob/HEAD/mkqa_eval_util.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":"11dc500c3a9d29b0"}},{"code_sha256_prefix":"833a3be37f55a115","entry":"map_f1_value","repo":"apple/ml-mkqa","repo_kind":"official","path":"mkqa_eval_util.py","file_url":"https://github.com/apple/ml-mkqa/blob/HEAD/mkqa_eval_util.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":"833a3be37f55a115"}},{"code_sha256_prefix":"d866f827b0e9464d","entry":"read_annotations","repo":"apple/ml-mkqa","repo_kind":"official","path":"mkqa_eval.py","file_url":"https://github.com/apple/ml-mkqa/blob/HEAD/mkqa_eval.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":"d866f827b0e9464d"}},{"code_sha256_prefix":"e2e26d4764ff96b4","entry":"read_predictions","repo":"apple/ml-mkqa","repo_kind":"official","path":"mkqa_eval.py","file_url":"https://github.com/apple/ml-mkqa/blob/HEAD/mkqa_eval.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":"e2e26d4764ff96b4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}