-
公开(公告)号：US09501759B2
公开(公告)日：2016-11-22
申请号：US13328924
申请日：2011-12-16
申请人： Jianfeng Gao , Xuedong Huang , Mei Li , Zhenghao Wang , Christopher John Brockett , William B. Dolan
发明人： Jianfeng Gao , Xuedong Huang , Mei Li , Zhenghao Wang , Christopher John Brockett , William B. Dolan
CPC分类号： G06Q10/10 , G06F17/30687 , G06Q30/0241
摘要： The subject disclosure is directed towards developing a translation model for mapping search query terms to document-related data. By processing user logs comprising search histories into word-aligned query-document pairs, the translation model may be trained using data, such as probabilities, corresponding to the word-aligned query-document pairs. After incorporating the translation model into model data for a search engine, the translation model is used may used as features for producing relevance scores for current search queries and ranking documents/advertisements according to relevance.
摘要翻译： 本发明旨在开发用于将搜索查询词语映射到文档相关数据的翻译模型。 通过将包括搜索历史的用户日志处理成字对齐的查询 - 文档对，可以使用对应于字对齐的查询 - 文档对的诸如概率的数据来训练翻译模型。 在将翻译模型合并到搜索引擎的模型数据中之后，使用翻译模型可以用作根据相关性产生当前搜索查询和排序文档/广告的相关性分数的特征。
-
2.发明授权User-modifiable word lattice display for editing documents and search queries 有权用户可修改的字格显示，用于编辑文档和搜索查询公开(公告)号：US08972240B2
公开(公告)日：2015-03-03
申请号：US13212973
申请日：2011-08-18
IPC分类号： G06F17/27 , G06F17/21 , G06F17/20 , G06F3/048 , G06F3/00 , G06F17/22 , G06F17/24 , G06F17/25 , G06F17/26 , G06F17/28 , G06F7/00 , G06F17/00 , G06F17/30 , G10L15/00 , G10L15/28 , G10L21/06 , G10L25/00 , G10L21/00
CPC分类号： G06F17/30637 , G06F17/2229 , G06F17/24 , G06F17/2795 , G06F17/2836
摘要： An “Interactive Word Lattice” provides a user interface for interacting with and selecting user-modifiable paths through a lattice-based representation of alternative suggested text segments in response to a user's text segment input, such as phrases, sentences, paragraphs, entire documents, etc. More specifically, the user input is provided to a trained paraphrase generation model that returns a plurality of alternative text segments having the same or similar meaning as the original user input. An interactive graphical lattice-based representation of the alternative text segments is then presented to the user. One or more words of each alternative text segment represents a “node” of the lattice, while each connection between nodes represents a lattice “edge. Both nodes and edges are user modifiable. Each possible path through the lattice corresponds to a different alternative text segment. Users select a path through the lattice to select an alternative text to the original input.
摘要翻译： “交互式词格”提供了一种用户界面，用于响应于用户的文本段输入，例如短语，句子，段落，整个文档，通过替代的建议文本段的基于格的表示来与用户可修改的路径交互并选择用户可修改的路径， 更具体地，将用户输入提供给经过训练的释义生成模型，其返回具有与原始用户输入相同或相似含义的多个备选文本段。 然后将替代文本段的交互式图形网格表示呈现给用户。 每个备选文本段的一个或多个单词表示网格的“节点”，而节点之间的每个连接表示网格“边缘”。 节点和边缘都是用户可修改的。 通过格子的每个可能的路径对应于不同的替代文本段。 用户选择通过格子的路径，以选择与原始输入的替代文本。
-
公开(公告)号：US20130103493A1
公开(公告)日：2013-04-25
申请号：US13328924
申请日：2011-12-16
申请人： Jianfeng Gao , Xuedong Huang , Mei Li , Zhenghao Wang , Christopher John Brockett , William B. Dolan
发明人： Jianfeng Gao , Xuedong Huang , Mei Li , Zhenghao Wang , Christopher John Brockett , William B. Dolan
CPC分类号： G06Q10/10 , G06F17/30687 , G06Q30/0241
摘要： The subject disclosure is directed towards developing a translation model for mapping search query terms to document-related data. By processing user logs comprising search histories into word-aligned query-document pairs, the translation model may be trained using data, such as probabilities, corresponding to the word-aligned query-document pairs. After incorporating the translation model into model data for a search engine, the translation model is used may used as features for producing relevance scores for current search queries and ranking documents/advertisements according to relevance.
摘要翻译： 本发明旨在开发用于将搜索查询词语映射到文档相关数据的翻译模型。 通过将包括搜索历史的用户日志处理成字对齐的查询 - 文档对，可以使用对应于字对齐的查询 - 文档对的诸如概率的数据来训练翻译模型。 在将翻译模型合并到搜索引擎的模型数据中之后，使用翻译模型可以用作根据相关性产生当前搜索查询和排序文档/广告的相关性分数的特征。
-
4.发明申请USER-MODIFIABLE WORD LATTICE DISPLAY FOR EDITING DOCUMENTS AND SEARCH QUERIES 有权用户可修改的字幕显示，用于编辑文档和搜索查询公开(公告)号：US20120296635A1
公开(公告)日：2012-11-22
申请号：US13212973
申请日：2011-08-18
IPC分类号： G06F17/27
CPC分类号： G06F17/30637 , G06F17/2229 , G06F17/24 , G06F17/2795 , G06F17/2836
摘要： An “Interactive Word Lattice” provides a user interface for interacting with and selecting user-modifiable paths through a lattice-based representation of alternative suggested text segments in response to a user's text segment input, such as phrases, sentences, paragraphs, entire documents, etc. More specifically, the user input is provided to a trained paraphrase generation model that returns a plurality of alternative text segments having the same or similar meaning as the original user input. An interactive graphical lattice-based representation of the alternative text segments is then presented to the user. One or more words of each alternative text segment represents a “node” of the lattice, while each connection between nodes represents a lattice “edge. Both nodes and edges are user modifiable. Each possible path through the lattice corresponds to a different alternative text segment. Users select a path through the lattice to select an alternative text to the original input.
摘要翻译： 交互词格子提供用户界面，用于响应于用户的文本段输入（例如短语，句子，段落，整个文档等），通过替代建议文本段的基于格的表示来与用户可修改路径进行交互和选择。 更具体地，将用户输入提供给经过训练的释义生成模型，其返回与原始用户输入具有相同或相似含义的多个备选文本段。 然后将替代文本段的交互式图形网格表示呈现给用户。 每个备选文本段的一个或多个字表示网格的节点，而节点之间的每个连接表示网格边缘。 节点和边缘都是用户可修改的。 通过格子的每个可能的路径对应于不同的替代文本段。 用户选择通过格子的路径，以选择与原始输入的替代文本。
-
5.发明申请Crowdsourced, Grounded Language for Intent Modeling in Conversational Interfaces 有权众所周知的语言对话接口中的意图建模公开(公告)号：US20130262114A1
公开(公告)日：2013-10-03
申请号：US13438751
申请日：2012-04-03
申请人： Christopher John Brockett , Piali Choudhury , William Brennan Dolan , Yun-Cheng Ju , Patrick Pantel , Noelle Mallory Sophy , Svitlana Volkova
发明人： Christopher John Brockett , Piali Choudhury , William Brennan Dolan , Yun-Cheng Ju , Patrick Pantel , Noelle Mallory Sophy , Svitlana Volkova
摘要： Different advantageous embodiments provide a crowdsourcing method for modeling user intent in conversational interfaces. One or more stimuli are presented to a plurality of describers. One or more sets of describer data are captured from the plurality of describers using a data collection mechanism. The one or more sets of describer data are processed to generate one or more models. Each of the one or more models is associated with a specific stimulus from the one or more stimuli.
摘要翻译： 不同的有利实施例提供了用于在会话界面中建模用户意图的众包方法。 一个或多个刺激被呈现给多个描述者。 使用数据收集机构从多个描述者捕获一组或多组描述数据。 一组或多组描述者数据被处理以产生一个或多个模型。 一个或多个模型中的每一个与来自一个或多个刺激的特定刺激相关联。
-
公开(公告)号：US20120096042A1
公开(公告)日：2012-04-19
申请号：US12907031
申请日：2010-10-19
IPC分类号： G06F17/30
CPC分类号： G06F17/30448
摘要： There is provided a computer-implemented method for user query reformulation. A graph is created to represent a relationship between previous user query terms. The graph may represent the previous user searches in n-grams that correspond to nodes. A random walk analysis is performed to determine probabilities that various n-grams corresponding to nodes of the graph could be used to effectively alter a user search term. The probabilities represent a quantification of relationships between nodes of the graph. A determination may be made regarding whether to reformulate the user query based on a relationship between a user search term in the user query and a graphed search term represented by a node of the graph. The determination takes into account a relationship between the user search term and the graphed search term.
摘要翻译： 提供了一种用于用户查询重新设计的计算机实现的方法。 创建一个图表来表示先前的用户查询词之间的关系。 该图可以代表与n个节点对应的先前用户搜索。 执行随机游走分析以确定可以使用对应于图的节点的各种n-gram来有效地改变用户搜索项的概率。 概率表示图的节点之间的关系的量化。 可以基于用户查询中的用户搜索项和由图的节点表示的图形搜索项之间的关系来确定是否重新形成用户查询。 该确定考虑了用户搜索项和图形搜索项之间的关系。
-
公开(公告)号：US08484016B2
公开(公告)日：2013-07-09
申请号：US12789472
申请日：2010-05-28
CPC分类号： G06F17/2827 , G06F17/2775 , G06F17/2795
摘要： A method is described herein that includes acts of receiving a selection of a first phrase in a first language and executing a random walk over a computer-implemented multipartite graph, wherein the multipartite-graph includes a first set of nodes that are representative of phrases in the first language, a second set of nodes that are representative of phrases in a second language, and edges between nodes that are representative of relationships between the respective phrases. The random walk includes traversals over edges of the graph between nodes. The method also includes the act of indicating that a second phrase in the first language is a paraphrase of the first phrase based at least in part upon the random walk.
摘要翻译： 本文描述的方法包括以第一语言接收第一短语的选择并且通过计算机实现的多部分图形执行随机游走的动作，其中所述多部分图包括表示第一组节点中的短语的第一组节点 第一语言，代表第二语言中的短语的第二组节点，以及代表各个短语之间的关系的节点之间的边缘。 随机游走包括在节点之间的图形边缘上的遍历。 该方法还包括指示第一语言中的第二短语至少部分地基于随机游走的第一短语的释义的动作。
-
公开(公告)号：US09092483B2
公开(公告)日：2015-07-28
申请号：US12907031
申请日：2010-10-19
IPC分类号： G06F17/30
CPC分类号： G06F17/30448
摘要： There is provided a computer-implemented method for user query reformulation. A graph is created to represent a relationship between previous user query terms. The graph may represent the previous user searches in n-grams that correspond to nodes. A random walk analysis is performed to determine probabilities that various n-grams corresponding to nodes of the graph could be used to effectively alter a user search term. The probabilities represent a quantification of relationships between nodes of the graph. A determination may be made regarding whether to reformulate the user query based on a relationship between a user search term in the user query and a graphed search term represented by a node of the graph. The determination takes into account a relationship between the user search term and the graphed search term.
摘要翻译： 提供了一种用于用户查询重新设计的计算机实现的方法。 创建一个图表来表示先前的用户查询词之间的关系。 该图可以代表与n个节点对应的先前用户搜索。 执行随机游走分析以确定可以使用对应于图的节点的各种n-gram来有效地改变用户搜索项的概率。 概率表示图的节点之间的关系的量化。 可以基于用户查询中的用户搜索项和由图的节点表示的图形搜索项之间的关系来确定是否重新形成用户查询。 该确定考虑了用户搜索项和图形搜索项之间的关系。
-
9.发明授权Interface and methods for collecting aligned editorial corrections into a database 有权将对齐的编辑修正收集到数据库中的界面和方法公开(公告)号：US08078451B2
公开(公告)日：2011-12-13
申请号：US11589126
申请日：2006-10-27
IPC分类号： G06F17/27 , G06F17/00 , G06F17/20 , G06F17/21 , G06F17/22 , G06F17/24 , G06F17/25 , G06F17/26 , G06F17/28
CPC分类号： G06F17/2827 , G06F17/24
摘要： A method for providing aligned editorial corrections to a database is discussed. The method includes receiving a first text in a language and organizing the first text into one or more sentences. The method further includes editing a copy of the first text to create a second text. The second text is in the language of the first text. The method further includes aligning the sentences of the first text with corresponding sentences of the second text storing the aligned sentences on a computer readable medium. A system for providing a data structure having aligned editorial corrections is also discussed. The system includes an alignment component for receiving a first text and organizing the first text into sentences. The system also includes a user interface configured to provide a second text, wherein the second text is an edited version of the first text in the language of the first text.
摘要翻译： 讨论了一种用于向数据库提供对齐的编辑修正的方法。 该方法包括以语言接收第一文本并将第一文本组织成一个或多个句子。 该方法还包括编辑第一文本的副本以创建第二文本。 第二个文本是第一个文本的语言。 该方法还包括将第一文本的句子与存储在计算机可读介质上的对准句子的第二文本的对应句子对齐。 还讨论了一种用于提供具有对准的编辑校正的数据结构的系统。 该系统包括用于接收第一文本并将第一文本组织成句子的对准部件。 该系统还包括被配置为提供第二文本的用户界面，其中第二文本是第一文本的语言的第一文本的编辑版本。
-
公开(公告)号：US20100293180A1
公开(公告)日：2010-11-18
申请号：US12467538
申请日：2009-05-18
IPC分类号： G06F17/30
CPC分类号： G06F17/30696
摘要： Conceptually related term identification technique embodiments are presented that involve identifying in the results of a search query, terms that are conceptually related to the search query terms. In one general embodiment, this is accomplished by first inputting the terms employed in a search query and the results of the search. Word tokens found in the search query terms are then identified, as are potential phrases that can be made from the identified word tokens. Conceptually related words and phrases are then identified in the search query results. These words and phrases correspond to the previously identified word tokens and potential phrases. The search query results are presented to a user on a display device in such a manner as to visually distinguish the conceptually related words and phrases from other words and phrases in the search query results.
摘要翻译： 提出了概念上相关的术语识别技术实施例，其涉及在搜索查询的结果中识别在概念上与搜索查询术语相关的术语。 在一个一般实施例中，这是通过首先输入在搜索查询中使用的术语和搜索结果来实现的。 然后识别在搜索查询术语中找到的词标记，以及可以从识别的词标记形成的潜在短语。 然后在搜索查询结果中识别概念上相关的单词和短语。 这些单词和短语对应于先前识别的词标记和潜在短语。 搜索查询结果以在视觉上区分搜索查询结果中的概念上相关的单词和短语与其他单词和短语的方式呈现给显示设备上的用户。
-
-
-
-
-
-
-
-
-
搜索结果
13 条记录 (耗时 0.019 秒)
