@misc{https://doi.org/10.48550/arxiv.2209.10655,
  doi = {10.48550/ARXIV.2209.10655},
  url = {https://arxiv.org/abs/2209.10655},
  author = {Ma, Xuezhe and Zhou, Chunting and Kong, Xiang and He, Junxian and Gui, Liangke and Neubig, Graham and May, Jonathan and Zettlemoyer, Luke},
  keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {Mega: Moving Average Equipped Gated Attention},
  publisher = {arXiv},
  year = {2022},
  copyright = {arXiv.org perpetual, non-exclusive license}
}

{"_id":"A3qHGtXaqCipkHGD5","bibbaseid":"ma-zhou-kong-he-gui-neubig-may-zettlemoyer-megamovingaverageequippedgatedattention-2022","author_short":["Ma, X.","Zhou, C.","Kong, X.","He, J.","Gui, L.","Neubig, G.","May, J.","Zettlemoyer, L."],"bibdata":{"bibtype":"misc","type":"misc","doi":"10.48550/ARXIV.2209.10655","url":"https://arxiv.org/abs/2209.10655","author":[{"propositions":[],"lastnames":["Ma"],"firstnames":["Xuezhe"],"suffixes":[]},{"propositions":[],"lastnames":["Zhou"],"firstnames":["Chunting"],"suffixes":[]},{"propositions":[],"lastnames":["Kong"],"firstnames":["Xiang"],"suffixes":[]},{"propositions":[],"lastnames":["He"],"firstnames":["Junxian"],"suffixes":[]},{"propositions":[],"lastnames":["Gui"],"firstnames":["Liangke"],"suffixes":[]},{"propositions":[],"lastnames":["Neubig"],"firstnames":["Graham"],"suffixes":[]},{"propositions":[],"lastnames":["May"],"firstnames":["Jonathan"],"suffixes":[]},{"propositions":[],"lastnames":["Zettlemoyer"],"firstnames":["Luke"],"suffixes":[]}],"keywords":"Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences","title":"Mega: Moving Average Equipped Gated Attention","publisher":"arXiv","year":"2022","copyright":"arXiv.org perpetual, non-exclusive license","bibtex":"@misc{https://doi.org/10.48550/arxiv.2209.10655,\n doi = {10.48550/ARXIV.2209.10655},\n url = {https://arxiv.org/abs/2209.10655},\n author = {Ma, Xuezhe and Zhou, Chunting and Kong, Xiang and He, Junxian and Gui, Liangke and Neubig, Graham and May, Jonathan and Zettlemoyer, Luke},\n keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},\n title = {Mega: Moving Average Equipped Gated Attention},\n publisher = {arXiv},\n year = {2022},\n copyright = {arXiv.org perpetual, non-exclusive license}\n}\n\n\n","author_short":["Ma, X.","Zhou, C.","Kong, X.","He, J.","Gui, L.","Neubig, G.","May, J.","Zettlemoyer, L."],"key":"https://doi.org/10.48550/arxiv.2209.10655","id":"https://doi.org/10.48550/arxiv.2209.10655","bibbaseid":"ma-zhou-kong-he-gui-neubig-may-zettlemoyer-megamovingaverageequippedgatedattention-2022","role":"author","urls":{"Paper":"https://arxiv.org/abs/2209.10655"},"keyword":["Machine Learning (cs.LG)","FOS: Computer and information sciences","FOS: Computer and information sciences"],"metadata":{"authorlinks":{}}},"bibtype":"misc","biburl":"https://jonmay.github.io/webpage/cutelabname/cutelabname.bib","dataSources":["hbZSwot2msWk92m5B","BnZgtH7HDESgbxKxt","j3Qzx9HAAC6WtJDHS","5eM3sAccSEpjSDHHQ"],"keywords":["machine learning (cs.lg)","fos: computer and information sciences","fos: computer and information sciences"],"search_terms":["mega","moving","average","equipped","gated","attention","ma","zhou","kong","he","gui","neubig","may","zettlemoyer"],"title":"Mega: Moving Average Equipped Gated Attention","year":2022}