{"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/neural-arabic-question-answering","title":"Neural Arabic Question Answering","arxiv_id":"1906.05394","date":"2019-06-12","proceeding":"WS 2019 8","authors":["Hussein Mozannar","Karl El Hajal","Elie Maamary","Hazem Hajj"],"abstract":"This paper tackles the problem of open domain factual Arabic question answering (QA) using Wikipedia as our knowledge source. This constrains the answer of any question to be a span of text in Wikipedia. Open domain QA for Arabic entails three challenges: annotated QA datasets in Arabic, large scale efficient information retrieval and machine reading comprehension. To deal with the lack of Arabic QA datasets we present the Arabic Reading Comprehension Dataset (ARCD) composed of 1,395 questions posed by crowdworkers on Wikipedia articles, and a machine translation of the Stanford Question Answering Dataset (Arabic-SQuAD). Our system for open domain question answering in Arabic (SOQAL) is based on two components: (1) a document retriever using a hierarchical TF-IDF approach and (2) a neural reading comprehension model using the pre-trained bi-directional transformer BERT. Our experiments on ARCD indicate the effectiveness of our approach with our BERT-based reader achieving a 61.3 F1 score, and our open domain system SOQAL achieving a 27.6 F1 score.","url_abs":"https://arxiv.org/abs/1906.05394v1","url_pdf":"https://arxiv.org/pdf/1906.05394v1.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":"neural-arabic-question-answering","repo_url":"https://github.com/husseinmozannar/SOQAL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"machine-reading-comprehension","task_name":"Machine Reading Comprehension"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"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":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"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":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[{"slug":"arcd","name":"ARCD","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.05394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05394"}},"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/husseinmozannar/SOQAL","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"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":"2c620cc10f52a944","entry":"gelu","repo":"husseinmozannar/SOQAL","repo_kind":"official","path":"bert/modeling.py","file_url":"https://github.com/husseinmozannar/SOQAL/blob/HEAD/bert/modeling.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2c620cc10f52a944"}},{"code_sha256_prefix":"0e2c9d9757a88fbb","entry":"get_activation","repo":"husseinmozannar/SOQAL","repo_kind":"official","path":"bert/modeling.py","file_url":"https://github.com/husseinmozannar/SOQAL/blob/HEAD/bert/modeling.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0e2c9d9757a88fbb"}},{"code_sha256_prefix":"c0cf1196424d4f71","entry":"softmax","repo":"husseinmozannar/SOQAL","repo_kind":"official","path":"soqal.py","file_url":"https://github.com/husseinmozannar/SOQAL/blob/HEAD/soqal.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c0cf1196424d4f71"}},{"code_sha256_prefix":"e9b032891a5228a4","entry":"exact_match_score","repo":"husseinmozannar/SOQAL","repo_kind":"official","path":"baselines_reading/evaluate_baselines.py","file_url":"https://github.com/husseinmozannar/SOQAL/blob/HEAD/baselines_reading/evaluate_baselines.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":"e9b032891a5228a4"}},{"code_sha256_prefix":"d917b8d6ed9310b1","entry":"f1_score","repo":"husseinmozannar/SOQAL","repo_kind":"official","path":"baselines_reading/evaluate_baselines.py","file_url":"https://github.com/husseinmozannar/SOQAL/blob/HEAD/baselines_reading/evaluate_baselines.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":"d917b8d6ed9310b1"}},{"code_sha256_prefix":"50958618b65e514e","entry":"get_assignment_map_from_checkpoint","repo":"husseinmozannar/SOQAL","repo_kind":"official","path":"bert/modeling.py","file_url":"https://github.com/husseinmozannar/SOQAL/blob/HEAD/bert/modeling.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":"50958618b65e514e"}},{"code_sha256_prefix":"e4b49776872650db","entry":"normalize_answer","repo":"husseinmozannar/SOQAL","repo_kind":"official","path":"baselines_reading/evaluate_baselines.py","file_url":"https://github.com/husseinmozannar/SOQAL/blob/HEAD/baselines_reading/evaluate_baselines.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":"e4b49776872650db"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}