{"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/comparing-attention-based-convolutional-and","title":"Comparing Attention-based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension","arxiv_id":"1808.08744","date":"2018-08-27","proceeding":"CONLL 2018 10","authors":["Matthias Blohm","Glorianna Jagfeld","Ekta Sood","Xiang Yu","Ngoc Thang Vu"],"abstract":"We propose a machine reading comprehension model based on the\ncompare-aggregate framework with two-staged attention that achieves\nstate-of-the-art results on the MovieQA question answering dataset. To\ninvestigate the limitations of our model as well as the behavioral difference\nbetween convolutional and recurrent neural networks, we generate adversarial\nexamples to confuse the model and compare to human performance. Furthermore, we\nassess the generalizability of our model by analyzing its differences to human\ninference,","url_abs":"http://arxiv.org/abs/1808.08744v1","url_pdf":"http://arxiv.org/pdf/1808.08744v1.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":"comparing-attention-based-convolutional-and","repo_url":"https://github.com/DigitalPhonetics/reading-comprehension","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"machine-reading-comprehension","task_name":"Machine Reading Comprehension"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.08744","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}