{"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/xor-qa-cross-lingual-open-retrieval-question","title":"XOR QA: Cross-lingual Open-Retrieval Question Answering","arxiv_id":"2010.11856","date":"2020-10-22","proceeding":"NAACL 2021 4","authors":["Akari Asai","Jungo Kasai","Jonathan H. Clark","Kenton Lee","Eunsol Choi","Hannaneh Hajishirzi"],"abstract":"Multilingual question answering tasks typically assume answers exist in the same language as the question. Yet in practice, many languages face both information scarcity -- where languages have few reference articles -- and information asymmetry -- where questions reference concepts from other cultures. This work extends open-retrieval question answering to a cross-lingual setting enabling questions from one language to be answered via answer content from another language. We construct a large-scale dataset built on questions from TyDi QA lacking same-language answers. Our task formulation, called Cross-lingual Open Retrieval Question Answering (XOR QA), includes 40k information-seeking questions from across 7 diverse non-English languages. Based on this dataset, we introduce three new tasks that involve cross-lingual document retrieval using multi-lingual and English resources. We establish baselines with state-of-the-art machine translation systems and cross-lingual pretrained models. Experimental results suggest that XOR QA is a challenging task that will facilitate the development of novel techniques for multilingual question answering. Our data and code are available at https://nlp.cs.washington.edu/xorqa.","url_abs":"https://arxiv.org/abs/2010.11856v3","url_pdf":"https://arxiv.org/pdf/2010.11856v3.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":"xor-qa-cross-lingual-open-retrieval-question","repo_url":"https://github.com/AkariAsai/XORQA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"xor-qa-cross-lingual-open-retrieval-question","repo_url":"https://github.com/jungokasai/XOR_QA_MTPipeline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"xor-qa-cross-lingual-open-retrieval-question","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":"articles","task_name":"Articles"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[{"slug":"xor-tydi-qa","name":"XOR-TYDI QA","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.11856","atlas_url":"https://app.syntology.ai/?focus=2010.11856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11856"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/jungokasai/XOR_QA_MTPipeline","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AkariAsai/XORQA","reach":null}],"summary":{"ran":6,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"listed":{"samples":9,"ran":8,"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":"a3826392847cbef3","entry":"count_trainable_parameters","repo":"mia-workshop/mia-shared-task-2022","repo_kind":"listed","path":"baseline/mGEN/callbacks_rag.py","file_url":"https://github.com/mia-workshop/mia-shared-task-2022/blob/HEAD/baseline/mGEN/callbacks_rag.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3826392847cbef3"}},{"code_sha256_prefix":"0d93b579cc96d791","entry":"evaluate_batch_e2e","repo":"mia-workshop/mia-shared-task-2022","repo_kind":"listed","path":"baseline/mGEN/eval_mgen.py","file_url":"https://github.com/mia-workshop/mia-shared-task-2022/blob/HEAD/baseline/mGEN/eval_mgen.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d93b579cc96d791"}},{"code_sha256_prefix":"295d9fdc5ce0b054","entry":"get_early_stopping_callback","repo":"mia-workshop/mia-shared-task-2022","repo_kind":"listed","path":"baseline/mGEN/callbacks_rag.py","file_url":"https://github.com/mia-workshop/mia-shared-task-2022/blob/HEAD/baseline/mGEN/callbacks_rag.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"295d9fdc5ce0b054"}},{"code_sha256_prefix":"130e15a144fbadf7","entry":"load_dpr_results","repo":"mia-workshop/mia-shared-task-2022","repo_kind":"listed","path":"baseline/mGEN/convert_dpr_retrieval_results_to_seq2seq.py","file_url":"https://github.com/mia-workshop/mia-shared-task-2022/blob/HEAD/baseline/mGEN/convert_dpr_retrieval_results_to_seq2seq.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"130e15a144fbadf7"}},{"code_sha256_prefix":"161e67ea95835704","entry":"load_passages","repo":"mia-workshop/mia-shared-task-2022","repo_kind":"listed","path":"baseline/mDPR/dense_retriever.py","file_url":"https://github.com/mia-workshop/mia-shared-task-2022/blob/HEAD/baseline/mDPR/dense_retriever.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"161e67ea95835704"}},{"code_sha256_prefix":"ed828b1e70bdbb40","entry":"normalize_answer","repo":"mia-workshop/mia-shared-task-2022","repo_kind":"listed","path":"eval_scripts/eval_xor_full.py","file_url":"https://github.com/mia-workshop/mia-shared-task-2022/blob/HEAD/eval_scripts/eval_xor_full.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed828b1e70bdbb40"}},{"code_sha256_prefix":"b66ea54438617d6c","entry":"postprocess","repo":"mia-workshop/mia-shared-task-2022","repo_kind":"listed","path":"baseline/mGEN/align_wikidata.py","file_url":"https://github.com/mia-workshop/mia-shared-task-2022/blob/HEAD/baseline/mGEN/align_wikidata.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b66ea54438617d6c"}},{"code_sha256_prefix":"fd4abbf0c46eb9be","entry":"tokenize_zh_text","repo":"mia-workshop/mia-shared-task-2022","repo_kind":"listed","path":"eval_scripts/eval_mkqa_all.py","file_url":"https://github.com/mia-workshop/mia-shared-task-2022/blob/HEAD/eval_scripts/eval_mkqa_all.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd4abbf0c46eb9be"}},{"code_sha256_prefix":"e2849ab65c6105e4","entry":"get_checkpoint_callback","repo":"mia-workshop/mia-shared-task-2022","repo_kind":"listed","path":"baseline/mGEN/callbacks_rag.py","file_url":"https://github.com/mia-workshop/mia-shared-task-2022/blob/HEAD/baseline/mGEN/callbacks_rag.py","link_basis":"harvester_set","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":"e2849ab65c6105e4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}