{"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/common-sense-beyond-english-evaluating-and","title":"Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning","arxiv_id":"2106.06937","date":"2021-06-13","proceeding":"ACL 2021 5","authors":["Bill Yuchen Lin","Seyeon Lee","Xiaoyang Qiao","Xiang Ren"],"abstract":"Commonsense reasoning research has so far been limited to English. We aim to evaluate and improve popular multilingual language models (ML-LMs) to help advance commonsense reasoning (CSR) beyond English. We collect the Mickey Corpus, consisting of 561k sentences in 11 different languages, which can be used for analyzing and improving ML-LMs. We propose Mickey Probe, a language-agnostic probing task for fairly evaluating the common sense of popular ML-LMs across different languages. In addition, we also create two new datasets, X-CSQA and X-CODAH, by translating their English versions to 15 other languages, so that we can evaluate popular ML-LMs for cross-lingual commonsense reasoning. To improve the performance beyond English, we propose a simple yet effective method -- multilingual contrastive pre-training (MCP). It significantly enhances sentence representations, yielding a large performance gain on both benchmarks.","url_abs":"https://arxiv.org/abs/2106.06937v1","url_pdf":"https://arxiv.org/pdf/2106.06937v1.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":"common-sense-beyond-english-evaluating-and","repo_url":"https://github.com/INK-USC/XCSR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[{"slug":"x-csqa","name":"X-CSQA","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.06937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06937"}},"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/INK-USC/XCSR","reach":{"status":"ok","spdx":"MIT"}}],"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":"01dbc46b29880c2d","entry":"convert_ABC_to_123","repo":"INK-USC/XCSR","repo_kind":"official","path":"xcsr_experiments/utils_multiple_choice.py","file_url":"https://github.com/INK-USC/XCSR/blob/HEAD/xcsr_experiments/utils_multiple_choice.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":"01dbc46b29880c2d"}},{"code_sha256_prefix":"c04ec1353ed9d926","entry":"convert_examples_to_features","repo":"INK-USC/XCSR","repo_kind":"official","path":"xcsr_experiments/utils_multiple_choice.py","file_url":"https://github.com/INK-USC/XCSR/blob/HEAD/xcsr_experiments/utils_multiple_choice.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":"c04ec1353ed9d926"}},{"code_sha256_prefix":"77aa6eb953e2376d","entry":"eval_npy","repo":"INK-USC/XCSR","repo_kind":"official","path":"xcsr_experiments/eval_utils.py","file_url":"https://github.com/INK-USC/XCSR/blob/HEAD/xcsr_experiments/eval_utils.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":"77aa6eb953e2376d"}},{"code_sha256_prefix":"95bb1d5c24ca301e","entry":"output_labels","repo":"INK-USC/XCSR","repo_kind":"official","path":"xcsr_experiments/eval_utils.py","file_url":"https://github.com/INK-USC/XCSR/blob/HEAD/xcsr_experiments/eval_utils.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":"95bb1d5c24ca301e"}},{"code_sha256_prefix":"3c241ecfe3749a6d","entry":"simple_accuracy","repo":"INK-USC/XCSR","repo_kind":"official","path":"xcsr_experiments/run_mcqa.py","file_url":"https://github.com/INK-USC/XCSR/blob/HEAD/xcsr_experiments/run_mcqa.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":"3c241ecfe3749a6d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}