{"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/recurrently-controlled-recurrent-networks","title":"Recurrently Controlled Recurrent Networks","arxiv_id":"1811.09786","date":"2018-11-24","proceeding":"NeurIPS 2018 12","authors":["Yi Tay","Luu Anh Tuan","Siu Cheung Hui"],"abstract":"Recurrent neural networks (RNNs) such as long short-term memory and gated\nrecurrent units are pivotal building blocks across a broad spectrum of sequence\nmodeling problems. This paper proposes a recurrently controlled recurrent\nnetwork (RCRN) for expressive and powerful sequence encoding. More concretely,\nthe key idea behind our approach is to learn the recurrent gating functions\nusing recurrent networks. Our architecture is split into two components - a\ncontroller cell and a listener cell whereby the recurrent controller actively\ninfluences the compositionality of the listener cell. We conduct extensive\nexperiments on a myriad of tasks in the NLP domain such as sentiment analysis\n(SST, IMDb, Amazon reviews, etc.), question classification (TREC), entailment\nclassification (SNLI, SciTail), answer selection (WikiQA, TrecQA) and reading\ncomprehension (NarrativeQA). Across all 26 datasets, our results demonstrate\nthat RCRN not only consistently outperforms BiLSTMs but also stacked BiLSTMs,\nsuggesting that our controller architecture might be a suitable replacement for\nthe widely adopted stacked architecture.","url_abs":"http://arxiv.org/abs/1811.09786v1","url_pdf":"http://arxiv.org/pdf/1811.09786v1.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":"recurrently-controlled-recurrent-networks","repo_url":"https://github.com/vanzytay/NIPS2018_RCRN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"answer-selection","task_name":"Answer Selection"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}