{"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/neural-semantic-encoders","title":"Neural Semantic Encoders","arxiv_id":"1607.04315","date":"2016-07-14","proceeding":"EACL 2017 4","authors":["Tsendsuren Munkhdalai","Hong Yu"],"abstract":"We present a memory augmented neural network for natural language\nunderstanding: Neural Semantic Encoders. NSE is equipped with a novel memory\nupdate rule and has a variable sized encoding memory that evolves over time and\nmaintains the understanding of input sequences through read}, compose and write\noperations. NSE can also access multiple and shared memories. In this paper, we\ndemonstrated the effectiveness and the flexibility of NSE on five different\nnatural language tasks: natural language inference, question answering,\nsentence classification, document sentiment analysis and machine translation\nwhere NSE achieved state-of-the-art performance when evaluated on publically\navailable benchmarks. For example, our shared-memory model showed an\nencouraging result on neural machine translation, improving an attention-based\nbaseline by approximately 1.0 BLEU.","url_abs":"http://arxiv.org/abs/1607.04315v3","url_pdf":"http://arxiv.org/pdf/1607.04315v3.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":"neural-semantic-encoders","repo_url":"https://bitbucket.org/tsendeemts/nse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"neural-semantic-encoders","repo_url":"https://github.com/Smerity/keras_snli","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"neural-semantic-encoders","repo_url":"https://github.com/saraswat/munkhdalai-nse","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-classification","task_name":"Sentence Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"NSE-NSE","rank_in_archive_order":86,"of":91,"metrics":{"BLEU score":"17.9"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"300D MMA-NSE encoders with attention","rank_in_archive_order":72,"of":98,"metrics":{"% Test Accuracy":"85.4","% Train Accuracy":"86.9","Parameters":"3.2m"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"300D NSE encoders","rank_in_archive_order":76,"of":98,"metrics":{"% Test Accuracy":"84.6","% Train Accuracy":"86.2","Parameters":"3.0m"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-wikiqa","task":"Question Answering","dataset":"WikiQA","model":"MMA-NSE attention","rank_in_archive_order":18,"of":25,"metrics":{"MAP":"0.6811","MRR":"0.6993"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-2-binary","task":"Sentiment Analysis","dataset":"SST-2 Binary classification","model":"Neural Semantic Encoder","rank_in_archive_order":63,"of":87,"metrics":{"Accuracy":"89.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1607.04315","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}