{"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/quasi-recurrent-neural-networks","title":"Quasi-Recurrent Neural Networks","arxiv_id":"1611.01576","date":"2016-11-05","proceeding":null,"authors":["James Bradbury","Stephen Merity","Caiming Xiong","Richard Socher"],"abstract":"Recurrent neural networks are a powerful tool for modeling sequential data,\nbut the dependence of each timestep's computation on the previous timestep's\noutput limits parallelism and makes RNNs unwieldy for very long sequences. We\nintroduce quasi-recurrent neural networks (QRNNs), an approach to neural\nsequence modeling that alternates convolutional layers, which apply in parallel\nacross timesteps, and a minimalist recurrent pooling function that applies in\nparallel across channels. Despite lacking trainable recurrent layers, stacked\nQRNNs have better predictive accuracy than stacked LSTMs of the same hidden\nsize. Due to their increased parallelism, they are up to 16 times faster at\ntrain and test time. Experiments on language modeling, sentiment\nclassification, and character-level neural machine translation demonstrate\nthese advantages and underline the viability of QRNNs as a basic building block\nfor a variety of sequence tasks.","url_abs":"http://arxiv.org/abs/1611.01576v2","url_pdf":"http://arxiv.org/pdf/1611.01576v2.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":"quasi-recurrent-neural-networks","repo_url":"https://github.com/JonathanRaiman/tensorflow_qrnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"quasi-recurrent-neural-networks","repo_url":"https://github.com/Kyubyong/quasi-rnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"quasi-recurrent-neural-networks","repo_url":"https://github.com/bzhangGo/lrn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"quasi-recurrent-neural-networks","repo_url":"https://github.com/francescodisalvo05/66DaysOfData","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"quasi-recurrent-neural-networks","repo_url":"https://github.com/montallen/qrnn-rna-localization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"quasi-recurrent-neural-networks","repo_url":"https://github.com/salesforce/pytorch-qrnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"quasi-recurrent-neural-networks","repo_url":"https://github.com/zhou059/w266-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"},{"task_slug":null,"task_name":"Setting-1/4"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"glove","method_name":"GloVe"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"masked-convolution","method_name":"Masked Convolution"},{"method_slug":"qrnn","method_name":"QRNN"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"zoneout","method_name":"Zoneout"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-iwslt2015-german","task":"Machine Translation","dataset":"IWSLT2015 German-English","model":"QRNN","rank_in_archive_order":15,"of":15,"metrics":{"BLEU score":"19.41"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1611.01576","atlas_url":"https://app.syntology.ai/?focus=1611.01576","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01576"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bzhangGo/lrn","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/salesforce/pytorch-qrnn","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JonathanRaiman/tensorflow_qrnn","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/montallen/qrnn-rna-localization","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhou059/w266-project","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Kyubyong/quasi-rnn","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/francescodisalvo05/66DaysOfData","reach":{"status":"ok"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9f08d6c7471510e3","entry":"get_ext_filename","repo":"JonathanRaiman/tensorflow_qrnn","repo_kind":"listed","path":"qrnn.py","file_url":"https://github.com/JonathanRaiman/tensorflow_qrnn/blob/HEAD/qrnn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f08d6c7471510e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}