{"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/abcnn-attention-based-convolutional-neural","title":"ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs","arxiv_id":"1512.05193","date":"2015-12-16","proceeding":"TACL 2016 1","authors":["Wenpeng Yin","Hinrich Schütze","Bing Xiang","Bo-Wen Zhou"],"abstract":"How to model a pair of sentences is a critical issue in many NLP tasks such\nas answer selection (AS), paraphrase identification (PI) and textual entailment\n(TE). Most prior work (i) deals with one individual task by fine-tuning a\nspecific system; (ii) models each sentence's representation separately, rarely\nconsidering the impact of the other sentence; or (iii) relies fully on manually\ndesigned, task-specific linguistic features. This work presents a general\nAttention Based Convolutional Neural Network (ABCNN) for modeling a pair of\nsentences. We make three contributions. (i) ABCNN can be applied to a wide\nvariety of tasks that require modeling of sentence pairs. (ii) We propose three\nattention schemes that integrate mutual influence between sentences into CNN;\nthus, the representation of each sentence takes into consideration its\ncounterpart. These interdependent sentence pair representations are more\npowerful than isolated sentence representations. (iii) ABCNN achieves\nstate-of-the-art performance on AS, PI and TE tasks.","url_abs":"http://arxiv.org/abs/1512.05193v4","url_pdf":"http://arxiv.org/pdf/1512.05193v4.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":"abcnn-attention-based-convolutional-neural","repo_url":"https://github.com/yinwenpeng/Answer_Selection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"abcnn-attention-based-convolutional-neural","repo_url":"https://github.com/Leputa/CIKM-AnalytiCup-2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"abcnn-attention-based-convolutional-neural","repo_url":"https://github.com/codykala/ABCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"abcnn-attention-based-convolutional-neural","repo_url":"https://github.com/galsang/ABCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"abcnn-attention-based-convolutional-neural","repo_url":"https://github.com/jastfkjg/semantic-matching","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"abcnn-attention-based-convolutional-neural","repo_url":"https://github.com/kinimod23/ATS_Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"abcnn-attention-based-convolutional-neural","repo_url":"https://github.com/shamalwinchurkar/question-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"abcnn-attention-based-convolutional-neural","repo_url":"https://github.com/sunsiqi26/Entailment-with-TensorFlow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"answer-selection","task_name":"Answer Selection"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"paraphrase-identification","task_name":"Paraphrase Identification"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1512.05193","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}