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

US20170263255A1 Scalable Endpoint-Dependent Natural Language Understanding 审中-公开
公开(公告)号：US20170263255A1
公开(公告)日：2017-09-14
申请号：US15067082
申请日：2016-03-10
申请人： Microsoft Technology Licensing, LLC
发明人： Minwoo Jeong , Ruhi Sarikaya
IPC分类号： G10L15/30 , G06F17/30 , G10L15/183
CPC分类号： G10L15/30 , G06F17/279 , G06F17/30634 , G06F17/30976 , G10L15/183
摘要： A computer-implemented technique is described for processing a linguistic item (e.g., a query) in an efficient and scalable manner. The technique interprets the linguistic item using a language understanding (LU) system in a manner that is based on a particular endpoint mechanism from which the linguistic item originated. The LU system may include an endpoint-independent subsystem, an endpoint-dependent subsystem, and a ranking component. The endpoint-independent subsystem interprets the linguistic item in a manner that is independent of the particular endpoint mechanism. The endpoint-dependent subsystem interprets the linguistic item in a manner that is dependent on the particular endpoint mechanism. The ranking component generates final interpretation results based on intermediate results generated by the endpoint-independent subsystem and the endpoint-dependent subsystem, e.g., by identifying the most likely interpretation of the linguistic item.

2. 发明申请

US20160247501A1 PRE-TRAINING AND/OR TRANSFER LEARNING FOR SEQUENCE TAGGERS 有权
标题翻译：针对序列标签的预培训和/或转学习
公开(公告)号：US20160247501A1
公开(公告)日：2016-08-25
申请号：US14625828
申请日：2015-02-19
申请人： Microsoft Technology Licensing, LLC
发明人： Young-Bum Kim , Minwoo Jeong , Ruhi Sarikaya
IPC分类号： G10L15/06 , G06N99/00 , G06F17/30 , G06F17/27 , G10L15/18
CPC分类号： G10L15/063 , G06F17/2775 , G06F17/30705 , G06N7/005 , G06N99/005 , G10L15/18 , G10L2015/0631
摘要： Systems and methods for pre-training a sequence tagger with unlabeled data, such as a hidden layered conditional random field model are provided. Additionally, systems and methods for transfer learning are provided. Accordingly, the systems and methods build more accurate, more reliable, and/or more efficient sequence taggers than previously utilized sequence taggers that are not pre-trained with unlabeled data and/or that are not capable of transfer learning/training.
摘要翻译：提供了使用未标记数据预处理序列标签器的系统和方法，例如隐藏的分层条件随机场模型。另外，提供用于传送学习的系统和方法。因此，系统和方法构建比未经过未经标记的数据预处理和/或不能传送学习/训练的先前使用的序列标签器更准确，更可靠和/或更有效的序列标记器。

3. 发明申请

US20160239758A1 TRAINING SYSTEMS AND METHODS FOR SEQUENCE TAGGERS 有权
标题翻译：训练系统和序列标签的方法
公开(公告)号：US20160239758A1
公开(公告)日：2016-08-18
申请号：US14623846
申请日：2015-02-17
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： Minwoo Jeong , Young-Bum Kim , Ruhi Sarikaya
IPC分类号： G06N99/00 , G06N7/00 , G06F17/30
CPC分类号： G06N99/005 , G06F17/2705 , G06F17/2785 , G06F17/30864 , G06N7/005
摘要： Systems and methods for or training as sequence tagger, such as conditional random field model. More specifically, the systems and methods train a sequence tagger utilizing partially labeled data from crowd-sourced data for a specific application and partially labeled data from search logs. Further, the systems and methods disclosed herein train a sequence tagger utilizing only partially labeled by utilizing a constrained lattice where each input value within the constrained lattice can have multiple candidate tags with confidence scores. Accordingly, the systems and methods provide for a more accurate sequence tagging system, a more reliable sequence tagging system, and a more efficient sequence tagging system in comparison to sequence taggers trained utilizing at least some fully-labeled training data.
摘要翻译：作为序列标签器的系统和方法或训练，如条件随机场模型。更具体地说，系统和方法使用来自针对特定应用的来自人群的数据的部分标记的数据和来自搜索日志的部分标记的数据来训练序列标签器。此外，本文公开的系统和方法通过利用受约束的格点仅利用部分标记的序列标签器来训练序列标签器，其中约束格点内的每个输入值可以具有具有置信度分数的多个候选标签。因此，与使用至少一些完全标记的训练数据训练的序列标签相比，系统和方法提供了更准确的序列标签系统，更可靠的序列标签系统和更有效的序列标签系统。

4. 发明授权

US10235358B2 Exploiting structured content for unsupervised natural language semantic parsing 有权
公开(公告)号：US10235358B2
公开(公告)日：2019-03-19
申请号：US13773269
申请日：2013-02-21
申请人： Microsoft Technology Licensing, LLC
发明人： Gokhan Tur , Dilek Hakkani-Tur , Larry Heck , Minwoo Jeong , Ye-Yi Wang
IPC分类号： G06F17/28 , G06F17/27
摘要： Structured web pages are accessed and parsed to obtain implicit annotation for natural language understanding tasks. Search queries that hit these structured web pages are automatically mined for information that is used to semantically annotate the queries. The automatically annotated queries may be used for automatically building statistical unsupervised slot filling models without using a semantic annotation guideline. For example, tags that are located on a structured web page that are associated with the search query may be used to annotate the query. The mined search queries may be filtered to create a set of queries that is in a form of a natural language query and/or remove queries that are difficult to parse. A natural language model may be trained using the resulting mined queries. Some queries may be set aside for testing and the model may be adapted using in-domain sentences that are not annotated. The models may be tested using these implicitly annotated natural-language-like queries in an unsupervised fashion.

5. 发明授权

US09792560B2 Training systems and methods for sequence taggers 有权
公开(公告)号：US09792560B2
公开(公告)日：2017-10-17
申请号：US14623846
申请日：2015-02-17
申请人： Microsoft Technology Licensing, LLC
发明人： Minwoo Jeong , Young-Bum Kim , Ruhi Sarikaya
IPC分类号： G06F15/18 , G06N99/00 , G06F17/30 , G06N7/00 , G06F17/27
CPC分类号： G06N99/005 , G06F17/2705 , G06F17/2785 , G06F17/30864 , G06N7/005
摘要： Systems and methods for or training as sequence tagger, such as conditional random field model. More specifically, the systems and methods train a sequence tagger utilizing partially labeled data from crowd-sourced data for a specific application and partially labeled data from search logs. Further, the systems and methods disclosed herein train a sequence tagger utilizing only partially labeled by utilizing a constrained lattice where each input value within the constrained lattice can have multiple candidate tags with confidence scores. Accordingly, the systems and methods provide for a more accurate sequence tagging system, a more reliable sequence tagging system, and a more efficient sequence tagging system in comparison to sequence taggers trained utilizing at least some fully-labeled training data.

6. 发明授权

US10229687B2 Scalable endpoint-dependent natural language understanding 有权
公开(公告)号：US10229687B2
公开(公告)日：2019-03-12
申请号：US15067082
申请日：2016-03-10
申请人： Microsoft Technology Licensing, LLC
发明人： Minwoo Jeong , Ruhi Sarikaya
IPC分类号： G10L15/00 , G10L15/30 , G06F17/30 , G10L15/183 , G06F17/27
摘要： A computer-implemented technique is described for processing a linguistic item (e.g., a query) in an efficient and scalable manner. The technique interprets the linguistic item using a language understanding (LU) system in a manner that is based on a particular endpoint mechanism from which the linguistic item originated. The LU system may include an endpoint-independent subsystem, an endpoint-dependent subsystem, and a ranking component. The endpoint-independent subsystem interprets the linguistic item in a manner that is independent of the particular endpoint mechanism. The endpoint-dependent subsystem interprets the linguistic item in a manner that is dependent on the particular endpoint mechanism. The ranking component generates final interpretation results based on intermediate results generated by the endpoint-independent subsystem and the endpoint-dependent subsystem, e.g., by identifying the most likely interpretation of the linguistic item.

7. 发明授权

US09875736B2 Pre-training and/or transfer learning for sequence taggers 有权
公开(公告)号：US09875736B2
公开(公告)日：2018-01-23
申请号：US14625828
申请日：2015-02-19
申请人： Microsoft Technology Licensing, LLC
发明人： Young-Bum Kim , Minwoo Jeong , Ruhi Sarikaya
IPC分类号： G10L15/06 , G06F17/27 , G06F17/30 , G06N99/00 , G10L15/18 , G06N7/00
CPC分类号： G10L15/063 , G06F17/2775 , G06F17/30705 , G06N7/005 , G06N99/005 , G10L15/18 , G10L2015/0631
摘要： Systems and methods for pre-training a sequence tagger with unlabeled data, such as a hidden layered conditional random field model are provided. Additionally, systems and methods for transfer learning are provided. Accordingly, the systems and methods build more accurate, more reliable, and/or more efficient sequence taggers than previously utilized sequence taggers that are not pre-trained with unlabeled data and/or that are not capable of transfer learning/training.

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