专利检索 ap:("Igor Podgorny" OR "Faraz Sharafi" OR "Matthew Cannon" OR "Pavlo Malynin" OR "Jeff Geisler" OR "Yason Khaburzaniya" OR "Greg Coulombe") AND inv:"Yason Khaburzaniya" 第 1 页

1.

发明授权
Misspelling correction based on deep learning architecture 有权

公开(公告)号：US11017167B1

公开(公告)日：2021-05-25

申请号：US16024550

申请日：2018-06-29

申请人： Igor Podgorny , Faraz Sharafi , Matthew Cannon , Pavlo Malynin , Jeff Geisler , Yason Khaburzaniya , Greg Coulombe

发明人： Igor Podgorny , Faraz Sharafi , Matthew Cannon , Pavlo Malynin , Jeff Geisler , Yason Khaburzaniya , Greg Coulombe

IPC分类号： G06F40/232 , G06N3/08 , G06K9/62 , G06N20/00 , G06F16/951

摘要： The invention relates to a method. The method includes receiving a flawed input comprising a domain specific misspelling. The method further includes encoding, by an encoder machine learning model executing on a computer processor, the flawed input on a per character basis to create a context vector. The method further includes decoding, by a decoder machine learning model executing on the computer processor, the context vector on the per character basis to create a rephrased input lacking the domain specific misspelling. The method further includes presenting the rephrased input.