专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20150095033A1 TECHNIQUES FOR UPDATING A PARTIAL DIALOG STATE 有权
标题翻译：更新部分对话状态的技术
公开(公告)号：US20150095033A1
公开(公告)日：2015-04-02
申请号：US14044802
申请日：2013-10-02
申请人： Microsoft Corporation
发明人： Daniel Boies , Ruhi Sarikaya , Alexandre Rochette , Zhaleh Feizollahi , Nikhil Ramesh
IPC分类号： G10L15/18
CPC分类号： G10L15/1815 , G06F17/2785 , G06F17/30654
摘要： Embodiments provide for tracking a partial dialog state as part of managing a dialog state space, but the embodiments are not so limited. A method of an embodiment jointly models partial state update and named entity recognition using a sequence-based classification or other model, wherein recognition of named entities and a partial state update can be performed in a single processing stage at runtime to generate a distribution over partial dialog states. A system of an embodiment is configured to generate a distribution over partial dialog states at runtime in part using a sequence classification decoding or other algorithm to generate one or more partial dialog state hypothesis and/or a confidence score or measure associated with each hypothesis. Other embodiments are included.
摘要翻译：实施例提供了用于跟踪部分对话状态作为管理对话状态空间的一部分，但是实施例不限于此。实施例的方法使用基于序列的分类或其他模型联合地模拟部分状态更新和命名实体识别，其中可以在运行时在单个处理阶段中执行命名实体的识别和部分状态更新，以生成部分分布对话状态。实施例的系统被配置为在运行时部分地使用序列分类解码或其他算法在部分对话状态下生成分布，以生成与每个假设相关联的一个或多个部分对话状态假设和/或置信度分数或度量。包括其他实施例。

2. 发明申请

US20150248886A1 Model Based Approach for On-Screen Item Selection and Disambiguation 有权
标题翻译：基于模型的屏幕选择和消歧的方法
公开(公告)号：US20150248886A1
公开(公告)日：2015-09-03
申请号：US14194964
申请日：2014-03-03
申请人： Microsoft Corporation
发明人： Ruhi Sarikaya , Fethiye Asli Celikyilmaz , Zhaleh Feizollahi , Larry Paul Heck , Dilek Z. Hakkani-Tur
IPC分类号： G10L15/18
CPC分类号： G10L15/1815 , G06F3/167 , G06F17/30654 , G10L15/00 , G10L15/22 , G10L2015/223 , G10L2015/228
摘要： A model-based approach for on-screen item selection and disambiguation is provided. An utterance may be received by a computing device in response to a display of a list of items for selection on a display screen. A disambiguation model may then be applied to the utterance. The disambiguation model may be utilized to determine whether the utterance is directed to at least one of the list of displayed items, extract referential features from the utterance and identify an item from the list corresponding to the utterance, based on the extracted referential features. The computing device may then perform an action which includes selecting the identified item associated with utterance.
摘要翻译：提供了一种基于模型的屏幕选项和消歧歧义方法。响应于在显示屏幕上显示用于选择的项目的列表，计算设备可以接收发声。然后可以将消歧模型应用于话语。消歧模型可以用于确定话语是否被引导到所显示的项目的列表中的至少一个，基于所提取的参考特征，从话语中提取参考特征并从对应于话语的列表中识别项目。然后，计算设备可以执行包括选择与话语相关联的所识别的项目的动作。

3. 发明申请

US20140278355A1 USING HUMAN PERCEPTION IN BUILDING LANGUAGE UNDERSTANDING MODELS 有权
标题翻译：在建筑语言理解模型中使用人类感觉
公开(公告)号：US20140278355A1
公开(公告)日：2014-09-18
申请号：US13826173
申请日：2013-03-14
申请人： MICROSOFT CORPORATION
发明人： Ruhi Sarikaya , Anoop Deoras , Fethiye Asli Celikyilmaz , Zhaleh Feizollahi
IPC分类号： G10L17/04
CPC分类号： G06F17/28 , G06F17/2785
摘要： An understanding model is trained to account for human perception of the perceived relative importance of different tagged items (e.g. slot/intent/domain). Instead of treating each tagged item as equally important, human perception is used to adjust the training of the understanding model by associating a perceived weight with each of the different predicted items. The relative perceptual importance of the different items may be modeled using different methods (e.g. as a simple weight vector, a model trained using features (lexical, knowledge, slot type, . . . ), and the like). The perceptual weight vector and/or or model are incorporated into the understanding model training process where items that are perceptually more important are weighted more heavily as compared to the items that are determined by human perception as less important.
摘要翻译：训练理解模型以考虑人类对不同标记项目（例如时隙/意图/域）的感知相对重要性的感知。不是将每个被标记的项目视为同样重要的，人的感知被用于通过将感知权重与每个不同的预测项相关联来调整理解模型的训练。可以使用不同的方法（例如，作为简单的权重向量，使用特征训练的模型（词汇，知识，时隙类型等））来对不同项目的相对感知重要性进行建模。感知权重向量和/或或模型被并入到理解模型训练过程中，其中感知上更重要的项目与由人类感知确定的项目相比不太重要的比较更加重。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式