{"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/query-based-attention-cnn-for-text-similarity","title":"Query-based Attention CNN for Text Similarity Map","arxiv_id":"1709.05036","date":"2017-09-15","proceeding":null,"authors":["Tzu-Chien Liu","Yu-Hsueh Wu","Hung-Yi Lee"],"abstract":"In this paper, we introduce Query-based Attention CNN(QACNN) for Text\nSimilarity Map, an end-to-end neural network for question answering. This\nnetwork is composed of compare mechanism, two-staged CNN architecture with\nattention mechanism, and a prediction layer. First, the compare mechanism\ncompares between the given passage, query, and multiple answer choices to build\nsimilarity maps. Then, the two-staged CNN architecture extracts features\nthrough word-level and sentence-level. At the same time, attention mechanism\nhelps CNN focus more on the important part of the passage based on the query\ninformation. Finally, the prediction layer find out the most possible answer\nchoice. We conduct this model on the MovieQA dataset using Plot Synopses only,\nand achieve 79.99% accuracy which is the state of the art on the dataset.","url_abs":"http://arxiv.org/abs/1709.05036v2","url_pdf":"http://arxiv.org/pdf/1709.05036v2.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":"query-based-attention-cnn-for-text-similarity","repo_url":"https://github.com/chun5212021202/ACM-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"query-based-attention-cnn-for-text-similarity","repo_url":"https://github.com/coderalo/QACNN-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-similarity","task_name":"text similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}