M
Michael Collins
Researcher at Google
Publications - 221
Citations - 30486
Michael Collins is an academic researcher from Google. The author has contributed to research in topics: Parsing & Dependency grammar. The author has an hindex of 72, co-authored 201 publications receiving 27871 citations. Previous affiliations of Michael Collins include AT&T Labs & Columbia University.
Papers
More filters
Journal Article
A multicenter, randomized, dose-finding study of gamma intracoronary radiation therapy to inhibit recurrent restenosis after stenting.
Matthew J. Price,Jeffrey W. Moses,Martin B. Leon,Roxana Mehran,Manuela Negoita,Alexandra J. Lansky,Michael Collins,Huan Giap,Ray Lin,Shirish Jani,Stephen Steuterman,Stephen Balter,Jack Dalton,Roberto Lipsztein,Prabhakar Tripuraneni,Paul S. Teirstein +15 more
TL;DR: In this article, the safety and efficacy of intracoronary radiation therapy (ICRT) with a dose of 17 Gray (Gy) compared to the currently recommended dose prescription of 14 Gy for the treatment of in-stent restenosis within bare metal stents was evaluated.
Proceedings ArticleDOI
Compact kernel models for acoustic modeling via random feature selection
TL;DR: A simple but effective method is proposed for learning compact random feature models that approximate non-linear kernel methods, in the context of acoustic modeling, that is able to explore a large number of non- linear features while maintaining a compact model via feature selection more efficiently than existing approaches.
Posted Content
Low-Resource Syntactic Transfer with Unsupervised Source Reordering
TL;DR: It is demonstrated that reordering the source treebanks before training on them for a target language improves the accuracy of languages outside the European language family.
Coping with success: The maintenance of therapeutic effect in aphasia
Michael Collins,Robert T. Wertz +1 more
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned.
Sewon Min,Jordan Boyd-Graber,Chris Alberti,Danqi Chen,Eunsol Choi,Michael Collins,Kelvin Guu,Hannaneh Hajishirzi,Kenton Lee,Jennimaria Palomaki,Colin Raffel,Adam Roberts,Tom Kwiatkowski,Patrick S. H. Lewis,Yuxiang Wu,Heinrich Küttler,Linqing Liu,Pasquale Minervini,Pontus Stenetorp,Sebastian Riedel,Sohee Yang,Minjoon Seo,Gautier Izacard,Fabio Petroni,Lucas Hosseini,Nicola De Cao,Edouard Grave,Ikuya Yamada,Sonse Shimaoka,Masatoshi Suzuki,Shumpei Miyawaki,Shun Sato,Ryo Takahashi,Jun Suzuki,Martin Fajcik,Martin Docekal,Karel Ondrej,Pavel Smrz,Hao Cheng,Yelong Shen,Xiaodong Liu,Pengcheng He,Weizhu Chen,Jianfeng Gao,Barlas Oguz,Xilun Chen,Vladimir Karpukhin,Stan Peshterliev,Dmytro Okhonko,Michael Sejr Schlichtkrull,Sonal Gupta,Yashar Mehdad,Wen-tau Yih +52 more
TL;DR: The EfficientQA competition as mentioned in this paper focused on open-domain question answering (QA), where systems take natural language questions as input and return natural language answers, and the aim of the competition was to build systems that can predict correct answers while also satisfying strict on-disk memory budgets.