{"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/kuisail-at-semeval-2020-task-12-bert-cnn-for","title":"KUISAIL at SemEval-2020 Task 12: BERT-CNN for Offensive Speech Identification in Social Media","arxiv_id":"2007.13184","date":"2020-07-26","proceeding":"SEMEVAL 2020","authors":["Ali Safaya","Moutasem Abdullatif","Deniz Yuret"],"abstract":"In this paper, we describe our approach to utilize pre-trained BERT models with Convolutional Neural Networks for sub-task A of the Multilingual Offensive Language Identification shared task (OffensEval 2020), which is a part of the SemEval 2020. We show that combining CNN with BERT is better than using BERT on its own, and we emphasize the importance of utilizing pre-trained language models for downstream tasks. Our system, ranked 4th with macro averaged F1-Score of 0.897 in Arabic, 4th with score of 0.843 in Greek, and 3rd with score of 0.814 in Turkish. Additionally, we present ArabicBERT, a set of pre-trained transformer language models for Arabic that we share with the community.","url_abs":"https://arxiv.org/abs/2007.13184v1","url_pdf":"https://arxiv.org/pdf/2007.13184v1.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":"kuisail-at-semeval-2020-task-12-bert-cnn-for","repo_url":"https://github.com/alisafaya/OffensEval2020","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"abuse-detection","task_name":"Abuse Detection"},{"task_slug":"language-identification","task_name":"Language Identification"}],"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":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.13184","atlas_url":"https://app.syntology.ai/?focus=2007.13184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.13184"}},"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/alisafaya/OffensEval2020","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"c86227bb02c3af92","entry":"preprocess_text","repo":"alisafaya/OffensEval2020","repo_kind":"official","path":"bert-cnn.py","file_url":"https://github.com/alisafaya/OffensEval2020/blob/HEAD/bert-cnn.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c86227bb02c3af92"}},{"code_sha256_prefix":"eb87a91f5c3d138a","entry":"strip_accents_and_lowercase","repo":"alisafaya/OffensEval2020","repo_kind":"official","path":"bert-cnn.py","file_url":"https://github.com/alisafaya/OffensEval2020/blob/HEAD/bert-cnn.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb87a91f5c3d138a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}