{"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/fastfusionnet-new-state-of-the-art-for","title":"FastFusionNet: New State-of-the-Art for DAWNBench SQuAD","arxiv_id":"1902.11291","date":"2019-02-28","proceeding":null,"authors":["Felix Wu","Boyi Li","Lequn Wang","Ni Lao","John Blitzer","Kilian Q. Weinberger"],"abstract":"In this technical report, we introduce FastFusionNet, an efficient variant of\nFusionNet [12]. FusionNet is a high performing reading comprehension\narchitecture, which was designed primarily for maximum retrieval accuracy with\nless regard towards computational requirements. For FastFusionNets we remove\nthe expensive CoVe layers [21] and substitute the BiLSTMs with far more\nefficient SRU layers [19]. The resulting architecture obtains state-of-the-art\nresults on DAWNBench [5] while achieving the lowest training and inference time\non SQuAD [25] to-date. The code is available at\nhttps://github.com/felixgwu/FastFusionNet.","url_abs":"http://arxiv.org/abs/1902.11291v2","url_pdf":"http://arxiv.org/pdf/1902.11291v2.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":"fastfusionnet-new-state-of-the-art-for","repo_url":"https://github.com/felixgwu/FastFusionNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"fastfusionnet-new-state-of-the-art-for","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":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"bilstm","method_name":"BiLSTM"},{"method_slug":"cove","method_name":"CoVe"},{"method_slug":"glove","method_name":"GloVe"},{"method_slug":"highway-layer","method_name":"Highway Layer"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"location-based-attention","method_name":"Location-based Attention"},{"method_slug":"sru","method_name":"SRU"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.11291","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}