{"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/learning-to-skim-text","title":"Learning to Skim Text","arxiv_id":"1704.06877","date":"2017-04-23","proceeding":"ACL 2017 7","authors":["Adams Wei Yu","Hongrae Lee","Quoc V. Le"],"abstract":"Recurrent Neural Networks are showing much promise in many sub-areas of\nnatural language processing, ranging from document classification to machine\ntranslation to automatic question answering. Despite their promise, many\nrecurrent models have to read the whole text word by word, making it slow to\nhandle long documents. For example, it is difficult to use a recurrent network\nto read a book and answer questions about it. In this paper, we present an\napproach of reading text while skipping irrelevant information if needed. The\nunderlying model is a recurrent network that learns how far to jump after\nreading a few words of the input text. We employ a standard policy gradient\nmethod to train the model to make discrete jumping decisions. In our benchmarks\non four different tasks, including number prediction, sentiment analysis, news\narticle classification and automatic Q\\&A, our proposed model, a modified LSTM\nwith jumping, is up to 6 times faster than the standard sequential LSTM, while\nmaintaining the same or even better accuracy.","url_abs":"http://arxiv.org/abs/1704.06877v2","url_pdf":"http://arxiv.org/pdf/1704.06877v2.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":"learning-to-skim-text","repo_url":"https://github.com/COMP6248-Reproducability-Challenge/Differentiables_FastAccurateTextClassification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-skim-text","repo_url":"https://github.com/tsujuifu/pytorch_lstm-shuttle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-skim-text","repo_url":"https://github.com/yasufumy/pytorch_lstm_jump","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-skim-text","repo_url":"https://github.com/zhaopku/LSTM-Jump-for-text-skimming","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.06877","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}