-
公开(公告)号：US10185713B1
公开(公告)日：2019-01-22
申请号：US14867932
申请日：2015-09-28
Applicant: Amazon Technologies, Inc.
Inventor： Michael Denkowski , Alon Lavie , Gregory Alan Hanneman , Austin Matthews , Matthew Ryan Fiorillo , Robert Thomas Olszewski , Christopher James Dyer , William Joseph Kaper , Alexandre Alexandrovich Klementiev , Gavin R. Jewell
Abstract: Technologies are disclosed herein for statistical machine translation. In particular, the disclosed technologies include extensions to conventional machine translation pipelines: the use of multiple domain-specific and non-domain-specific dynamic language translation models and language models; cluster-based language models; and large-scale discriminative training. Incremental update technologies are also disclosed for use in updating a machine translation system in four areas: word alignment; translation modeling; language modeling; and parameter estimation. A mechanism is also disclosed for training and utilizing a runtime machine translation quality classifier for estimating the quality of machine translations without the benefit of reference translations. The runtime machine translation quality classifier is generated in a manner to offset imbalances in the number of training instances in various classes, and to assign a greater penalty to the misclassification of lower-quality translations as higher-quality translations than to misclassification of higher-quality translations as lower-quality translations.
-
Patent Agency Ranking
公开(公告)号：US09692811B1
公开(公告)日：2017-06-27
申请号：US14286539
申请日：2014-05-23
Applicant: Amazon Technologies, Inc.
Inventor： Brian Jaffery Tajuddin , Carlos Alejandro Arguelles , Jeremy Boynes , Adam Lloyd Days , Gavin R. Jewell , Erin Harding Kraemer , Jeenandra Kumar Uttamchand , Manoj Srivastava , Tyson Christopher Trautmann , Praveen Kambam Sugavanam
Abstract: Optimization preferences are defined for optimizing execution of a distributed application. Candidate sets of application parameter values may be tested in test execution environments. Measures of performance for metrics of interest are determined based upon the execution of the distributed application using the candidate sets of application parameter values. Utility curves may be utilized to compute measures of effectiveness for metrics of interest. A multi-attribute rollup operation may utilize the computed measures of effectiveness and weights to compute a grand measure of merit (MOM) for the candidate sets of application parameter values. An optimized set of application parameter values may then be selected based upon the computed grand MOMs. The optimized set of application parameter values may be deployed to a production execution environment executing the distributed application. Production safe application parameters might also be identified and utilized to optimize execution of the distributed application in a production execution environment.
-
公开(公告)号：US10666716B1
公开(公告)日：2020-05-26
申请号：US15629656
申请日：2017-06-21
Applicant: Amazon Technologies, Inc.
Inventor： Brian Jaffery Tajuddin , Carlos Alejandro Arguelles , Jeremy Boynes , Adam Lloyd Days , Gavin R. Jewell , Erin Harding Kraemer , Jeenandra Kumar Uttamchand , Manoj Srivastava , Tyson Christopher Trautmann , Praveen Kambam Sugavanam
Abstract: Optimization preferences are defined for optimizing execution of a distributed application. Candidate sets of application parameter values may be tested in test execution environments. Measures of performance for metrics of interest are determined based upon the execution of the distributed application using the candidate sets of application parameter values. Utility curves may be utilized to compute measures of effectiveness for metrics of interest. A multi-attribute rollup operation may utilize the computed measures of effectiveness and weights to compute a grand measure of merit (MOM) for the candidate sets of application parameter values. An optimized set of application parameter values may then be selected based upon the computed grand MOMs. The optimized set of application parameter values may be deployed to a production execution environment executing the distributed application. Production safe application parameters might also be identified and utilized to optimize execution of the distributed application in a production execution environment.
-
公开(公告)号：US09959271B1
公开(公告)日：2018-05-01
申请号：US14868083
申请日：2015-09-28
Applicant: Amazon Technologies, Inc.
Inventor： Kartik Goyal , Alon Lavie , Michael Denkowski , Gregory Alan Hanneman , Matthew Ryan Fiorillo , Robert Thomas Olszewski , Ehud Hershkovich , William Joseph Kaper , Alexandre Alexandrovich Klementiev , Gavin R. Jewell
CPC classification number: G06F17/2818 , G06F17/2854
Abstract: Technologies are disclosed herein for statistical machine translation. In particular, the disclosed technologies include extensions to conventional machine translation pipelines: the use of multiple domain-specific and non-domain-specific dynamic language translation models and language models; cluster-based language models; and large-scale discriminative training. Incremental update technologies are also disclosed for use in updating a machine translation system in four areas: word alignment; translation modeling; language modeling; and parameter estimation. A mechanism is also disclosed for training and utilizing a runtime machine translation quality classifier for estimating the quality of machine translations without the benefit of reference translations. The runtime machine translation quality classifier is generated in a manner to offset imbalances in the number of training instances in various classes, and to assign a greater penalty to the misclassification of lower-quality translations as higher-quality translations than to misclassification of higher-quality translations as lower-quality translations.
-
公开(公告)号：US09710322B2
公开(公告)日：2017-07-18
申请号：US14828381
申请日：2015-08-17
Applicant: Amazon Technologies, Inc.
Inventor： Gavin R. Jewell , Luke F. Kearney
CPC classification number: G06F11/079 , G06F11/0706 , G06F11/0784 , H04L41/0866 , H04L43/04
Abstract: Systems and methods are provided for mapping dependencies between system components and for analyzing and acting on possible root causes for anomalies experienced by the system components. Aspects of the present disclosure may present for display information associated with the dependency maps and ranked lists of possible root causes of anomalies. Ranking comprises determination of which operating parameters of related system components, when anomalous, will have the greatest effect on the operation of monitored system components. When possible root causes are ranked, notifications may be issued to alert administrators or other systems of the anomaly and the likely root causes.
-
公开(公告)号：US20150358208A1
公开(公告)日：2015-12-10
申请号：US14828381
申请日：2015-08-17
Applicant: Amazon Technologies, Inc.
Inventor： Gavin R. Jewell , Luke F. Kearney
CPC classification number: G06F11/079 , G06F11/0706 , G06F11/0784 , H04L41/0866 , H04L43/04
Abstract: Systems and methods are provided for mapping dependencies between system components and for analyzing and acting on possible root causes for anomalies experienced by the system components. Aspects of the present disclosure may present for display information associated with the dependency maps and ranked lists of possible root causes of anomalies. Ranking comprises determination of which operating parameters of related system components, when anomalous, will have the greatest effect on the operation of monitored system components. When possible root causes are ranked, notifications may be issued to alert administrators or other systems of the anomaly and the likely root causes.
Abstract translation: 提供了系统和方法，用于映射系统组件之间的依赖关系，并用于分析并对系统组件所经历的异常的可能根本原因起作用。 本公开的方面可以呈现用于与依赖图相关联的显示信息和异常的可能根本原因的排序列表。 排名包括确定相关系统组件的哪些运行参数在异常时对监控系统组件的运行影响最大。 当可能的根本原因排名时，可能会发出通知以警告管理员或其他系统的异常和可能的根本原因。
-
-
-
-
-
Search Results
6
records
(took 0.033 seconds)
