{"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/fast-reading-comprehension-with-convnets","title":"Fast Reading Comprehension with ConvNets","arxiv_id":"1711.04352","date":"2017-11-12","proceeding":"ICLR 2018 1","authors":["Felix Wu","Ni Lao","John Blitzer","Guandao Yang","Kilian Weinberger"],"abstract":"State-of-the-art deep reading comprehension models are dominated by recurrent\nneural nets. Their sequential nature is a natural fit for language, but it also\nprecludes parallelization within an instances and often becomes the bottleneck\nfor deploying such models to latency critical scenarios. This is particularly\nproblematic for longer texts. Here we present a convolutional architecture as\nan alternative to these recurrent architectures. Using simple dilated\nconvolutional units in place of recurrent ones, we achieve results comparable\nto the state of the art on two question answering tasks, while at the same time\nachieving up to two orders of magnitude speedups for question answering.","url_abs":"http://arxiv.org/abs/1711.04352v1","url_pdf":"http://arxiv.org/pdf/1711.04352v1.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":"fast-reading-comprehension-with-convnets","repo_url":"https://github.com/felixgwu/FastFusionNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"fast-reading-comprehension-with-convnets","repo_url":"https://github.com/yellowpsyduck/OccamFusionNet","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":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.04352","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}