{"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/automatic-spanish-translation-of-the-squad","title":"Automatic Spanish Translation of the SQuAD Dataset for Multilingual Question Answering","arxiv_id":"1912.05200","date":"2019-12-11","proceeding":null,"authors":["Casimiro Pio Carrino","Marta R. Costa-jussà","José A. R. Fonollosa"],"abstract":"Recently, multilingual question answering became a crucial research topic, and it is receiving increased interest in the NLP community. However, the unavailability of large-scale datasets makes it challenging to train multilingual QA systems with performance comparable to the English ones. In this work, we develop the Translate Align Retrieve (TAR) method to automatically translate the Stanford Question Answering Dataset (SQuAD) v1.1 to Spanish. We then used this dataset to train Spanish QA systems by fine-tuning a Multilingual-BERT model. Finally, we evaluated our QA models with the recently proposed MLQA and XQuAD benchmarks for cross-lingual Extractive QA. Experimental results show that our models outperform the previous Multilingual-BERT baselines achieving the new state-of-the-art value of 68.1 F1 points on the Spanish MLQA corpus and 77.6 F1 and 61.8 Exact Match points on the Spanish XQuAD corpus. The resulting, synthetically generated SQuAD-es v1.1 corpora, with almost 100% of data contained in the original English version, to the best of our knowledge, is the first large-scale QA training resource for Spanish.","url_abs":"https://arxiv.org/abs/1912.05200v2","url_pdf":"https://arxiv.org/pdf/1912.05200v2.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":"automatic-spanish-translation-of-the-squad","repo_url":"https://github.com/ccasimiro88/TranslateAlignRetrieve","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"automatic-spanish-translation-of-the-squad","repo_url":"https://github.com/aleksac99/SQuAD-SR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"automatic-spanish-translation-of-the-squad","repo_url":"https://github.com/lmarent/TranslateAlignRetrieve","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"tar","task_name":"TAR"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.05200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.05200"}},"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/ccasimiro88/TranslateAlignRetrieve","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lmarent/TranslateAlignRetrieve","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aleksac99/SQuAD-SR","reach":{"status":"ok"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1},"listed":{"samples":2,"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":"bdf7fdc43f326b54","entry":"average_len","repo":"ccasimiro88/TranslateAlignRetrieve","repo_kind":"official","path":"src/tar/src/nmt/utils.py","file_url":"https://github.com/ccasimiro88/TranslateAlignRetrieve/blob/HEAD/src/tar/src/nmt/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":"bdf7fdc43f326b54"}},{"code_sha256_prefix":"f1dd0f81b1aa5716","entry":"remove_line_breaks","repo":"lmarent/TranslateAlignRetrieve","repo_kind":"listed","path":"src/tar/src/retrieve/translate_retrieve_squad_utils.py","file_url":"https://github.com/lmarent/TranslateAlignRetrieve/blob/HEAD/src/tar/src/retrieve/translate_retrieve_squad_utils.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":"f1dd0f81b1aa5716"}},{"code_sha256_prefix":"1d8415fec6d4696b","entry":"sentence_len_histogram","repo":"ccasimiro88/TranslateAlignRetrieve","repo_kind":"official","path":"src/tar/src/nmt/utils.py","file_url":"https://github.com/ccasimiro88/TranslateAlignRetrieve/blob/HEAD/src/tar/src/nmt/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":"1d8415fec6d4696b"}},{"code_sha256_prefix":"1e4928b96c9f617a","entry":"translate","repo":"lmarent/TranslateAlignRetrieve","repo_kind":"listed","path":"src/tar/src/retrieve/translate_retrieve_utils.py","file_url":"https://github.com/lmarent/TranslateAlignRetrieve/blob/HEAD/src/tar/src/retrieve/translate_retrieve_utils.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":"1e4928b96c9f617a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}