公开(公告)号：US09812124B1

公开(公告)日：2017-11-07

申请号：US15624339

申请日：2017-06-15

Applicant: Google Inc.

Inventor： Jakob D. Uszkoreit ,  Percy Liang ,  Daniel M. Bikel

IPC: G06F17/27 ,  G10L15/18 ,  G10L15/22

CPC classification number: G10L15/1822 ,  G06F17/27 ,  G06F17/2705 ,  G06F17/274 ,  G06F17/2785 ,  G10L15/22 ,  G10L2015/223

Abstract: A language processing system identifies first command input sentences that do not successfully parse by any parsing rule in a set of parsing rules. Each of the parsing rules is associated with an action, and a user device performs the action associated with a parsing rule in response to an input sentence being successfully parsed by the parsing rule. For each of these identified first sentences, the system determines whether the first input sentence has an underserving signal that is indicative of one or more actions being underserved. If the first sentence has the underserving signal, then the first sentence is selected as a candidate input sentence. Each candidate input sentence is provided to an action analysis processes that determines whether a candidate input sentence is to be associated with one action, and upon a positive determination generates a parsing rule for the candidate input sentence.

公开(公告)号：US09280970B1

公开(公告)日：2016-03-08

申请号：US13926669

申请日：2013-06-25

Applicant: Google Inc.

Inventor： Jakob D. Uszkoreit ,  Percy Liang ,  Daniel M. Bikel

IPC: G10L15/18

CPC classification number: G10L15/1822 ,  G10L15/083 ,  G10L15/193

Abstract: A language processing system uses a lattice parser that semantically parses a command input represented by a lattice. The parser receives a hypotheses space of outputs as encoded in a lattice. Annotations of the input are projected back into the lattice and then lattice parsing is performed to rectify with the annotations. Parsing rules are applied to path fragments in the lattice. The rules that successfully parse from the start node to the end node of the lattice are used to determine whether the command input sentence invokes a specific action, and if so, what arguments are to be passed to the invocation of the action.

Abstract translation: 语言处理系统使用语义分析由格子表示的命令输入的点阵解析器。 解析器接收以格子编码的输出的假设空间。 将输入的注释投射回格子，然后执行格子解析以用注释进行纠正。 解析规则应用于格子中的路径片段。 用于从起始节点到网格的结束节点成功解析的规则用于确定命令输入句是否调用特定的动作，如果是，则将传递给动作调用的参数。

公开(公告)号：US09251202B1

公开(公告)日：2016-02-02

申请号：US13926649

申请日：2013-06-25

Applicant: Google Inc.

Inventor： Jakob D. Uszkoreit ,  Percy Liang ,  Daniel M. Bikel ,  Pravir K. Gupta ,  Omer Bar-or

IPC: G06F17/30

CPC classification number: G06F17/30864 ,  G06F17/30672

Abstract: A system determines search hypotheses for a search query, each search hypothesis defining a search type and respectively corresponding to a resource corpus of a type that matches the search type; for each search hypothesis, generate a hypothesis search query based on the search query and the search type and submits the hypothesis search query to a search service to determine a search hypothesis score, and for each search hypothesis having a search hypothesis score meeting a search hypothesis threshold, providing search results for the search operation performed for the hypothesis search query determined for the search hypothesis; and for each search hypothesis not having a search hypothesis score meeting a search hypothesis threshold, not providing search results for the search operation performed for the hypothesis search query determined for the search hypothesis.

Abstract translation: 系统确定搜索查询的搜索假设，每个搜索假设定义搜索类型并且分别对应于与搜索类型匹配的类型的资源语料库; 对于每个搜索假设，基于搜索查询和搜索类型生成假设搜索查询，并将搜索查询提交给搜索服务以确定搜索假设得分，并且对于具有满足搜索假设的搜索假设得分的每个搜索假设 提供针对为搜索假设确定的假设搜索查询执行的搜索操作的搜索结果; 并且对于不具有满足搜索假设阈值的搜索假设得分的每个搜索假设，不提供针对为搜索假设确定的假设搜索查询执行的搜索操作的搜索结果。

公开(公告)号：US09092505B1

公开(公告)日：2015-07-28

申请号：US13926591

申请日：2013-06-25

Applicant: Google Inc.

Inventor： Jakob D. Uszkoreit ,  Ashish Venugopal ,  Daniel M. Bikel

IPC: G06F17/30

CPC classification number: G06F17/28 ,  G06F17/2705 ,  G06F17/30598 ,  G06F17/30601 ,  G06F17/30705 ,  G06F17/3071 ,  G06F17/30713

Abstract: A method includes accessing command sentences stored in a data store, wherein each command sentence is a collection of n-grams and each command sentence includes at least one n-gram that is a non-terminal n-gram that maps to a non-terminal type, and wherein the command sentences include non-terminal n-grams that collectively map to a plurality of different non-terminal types; for each of the non-terminal types: identifying n-gram spans; determining clusters of the n-gram spans, each cluster including n-gram spans meeting a measure of similarity of n-grams spans that belong to the cluster; and for each cluster of n-gram spans, determining, from the n-gram spans belonging to the cluster, a new non-terminal type to which the terminal n-grams of the n-gram spans map.

Abstract translation: 一种方法包括访问存储在数据存储中的命令句，其中每个命令句是n-gram的集合，并且每个命令句包括至少一个n-gram，其是映射到非终端的非终端n-gram 类型，并且其中所述命令句子包括共同映射到多个不同非终端类型的非终端n-gram; 对于每个非终端类型：识别n-gram跨度; 确定n-gram跨度的群集，每个群集包括满足属于群集的n-gram跨度的相似性度量的n-gram跨度; 并且对于n-gram跨越的每个群集，从属于群集的n-gram跨度确定n-gram跨度的终端n-gram映射的新的非终端类型。

公开(公告)号：US09489378B1

公开(公告)日：2016-11-08

申请号：US14792112

申请日：2015-07-06

Applicant: Google Inc.

Inventor： Jakob D. Uszkoreit ,  Ashish Venugopal ,  Daniel M. Bikel

IPC: G06F17/30 ,  G06F17/28 ,  G06F17/27

CPC classification number: G06F17/28 ,  G06F17/2705 ,  G06F17/30598 ,  G06F17/30601 ,  G06F17/30705 ,  G06F17/3071 ,  G06F17/30713

Abstract: A method includes accessing command sentences stored in a data store, wherein each command sentence is a collection of n-grams and each command sentence includes at least one n-gram that is a non-terminal n-gram that maps to a non-terminal type, and wherein the command sentences include non-terminal n-grams that collectively map to a plurality of different non-terminal types; for each of the non-terminal types: identifying n-gram spans; determining clusters of the n-gram spans, each cluster including n-gram spans meeting a measure of similarity of n-grams spans that belong to the cluster; and for each cluster of n-gram spans, determining, from the n-gram spans belonging to the cluster, a new non-terminal type to which the terminal n-grams of the n-gram spans map.

Abstract translation: 一种方法包括访问存储在数据存储中的命令句，其中每个命令句是n-gram的集合，并且每个命令句包括至少一个n-gram，其是映射到非终端的非终端n-gram 类型，并且其中所述命令句子包括共同映射到多个不同非终端类型的非终端n-gram; 对于每个非终端类型：识别n-gram跨度; 确定n-gram跨度的群集，每个群集包括满足属于群集的n-gram跨度的相似性度量的n-gram跨度; 并且对于n-gram跨越的每个群集，从属于群集的n-gram跨度确定n-gram跨度的终端n-gram映射的新的非终端类型。

公开(公告)号：US09448994B1

公开(公告)日：2016-09-20

申请号：US14040012

申请日：2013-09-27

Applicant: Google Inc.

Inventor： Jakob D. Uszkoreit

IPC: G06F17/28

CPC classification number: G06F17/28 ,  G06F17/30014 ,  G06F17/3053 ,  G06F17/30876 ,  G06F17/30882

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for rating participants based on emotive feedback. In one aspect, a method includes identifying a first resource that includes a form associated with a particular action, identifying, using one or more computers, a second resource that references the form of the first resource, identifying anchor text in the second resource that references the form, and adding the identified anchor text to a set of phrases that is used for generating an action initiation grammar associated with the particular action.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于基于情绪反馈评估参与者。 在一个方面，一种方法包括识别包括与特定动作相关联的表单的第一资源，使用一个或多个计算机识别引用第一资源的形式的第二资源，识别第二资源中的锚文本 并且将所识别的锚文本添加到用于生成与特定动作相关联的动作起始语法的一组短语中。

公开(公告)号：US20160078131A1

公开(公告)日：2016-03-17

申请号：US14644803

申请日：2015-03-11

Applicant: Google Inc.

Inventor： Ashish Venugopal ,  Jakob D. Uszkoreit ,  John Blitzer ,  Edward Everett Anderson

IPC: G06F17/30

CPC classification number: G06F16/951 ,  G06F16/334

Abstract: The present disclosure relates to evaluating different semantic interpretations of a search query. One example method includes obtaining a set of search results for a particular search query submitted to a search engine; obtaining a set of semantic interpretations for the particular search query; obtaining, for each semantic interpretation of the set, a canonical search query; generating a modified search query based at least in part on the particular search query and the canonical search query for the semantic interpretation; obtaining a set of search results for the modified search query for the semantic interpretation; and determining, for each semantic interpretation of the set, a degree of similarity between (i) the set of search results of the modified search query for the semantic interpretation, and (ii) the set of search results for the particular search query.

Abstract translation: 本公开涉及评估搜索查询的不同语义解释。 一个示例性方法包括获得提交给搜索引擎的特定搜索查询的一组搜索结果; 为特定搜索查询获得一组语义解释; 对于集合的每个语义解释获得规范搜索查询; 至少部分地基于用于语义解释的特定搜索查询和规范搜索查询来生成修改的搜索查询; 获取用于语义解释的经修改的搜索查询的一组搜索结果; 以及为所述集合的每个语义解释确定（i）用于所述语义解释的所述经修改的搜索查询的搜索结果集合和（ii）所述特定搜索查询的搜索结果集合之间的相似度。

公开(公告)号：US09183196B1

公开(公告)日：2015-11-10

申请号：US13926915

申请日：2013-06-25

Applicant: Google Inc.

Inventor： Jakob D. Uszkoreit ,  Percy Liang ,  Daniel M. Bikel

IPC: G06F17/27 ,  G06F17/28

CPC classification number: G06F17/278 ,  G06F17/2705 ,  G06F17/271 ,  G06F17/2715 ,  G06F17/2755 ,  G06F17/28

Abstract: A language processing system uses annotation services that are external to the language processing system to identify n-grams that identify entities in an input sentence. The n-grams are annotated by the annotation services. The annotations are used to determine which n-grams, if any, correspond to instances of an entity type (e.g., values for a variable or terminals for a non-terminal). After determining which n-grams correspond to entity types, parse initializations are generated for parsing rules and parses for each rule are attempted. The rules that successfully parse are used to determine whether the input sentence invokes a specific action, and if so, what arguments are to be passed to the invocation of the action.

Abstract translation: 语言处理系统使用语言处理系统外部的注释服务来识别识别输入句中的实体的n-gram。 n-gram由注释服务注释。 注释用于确定哪个n克（如果有的话）对应于实体类型的实例（例如，用于非终端的变量或终端的值）。 在确定哪些n-gram对应于实体类型之后，将生成解析初始化以用于解析规则，并尝试对每个规则进行解析。 成功解析的规则用于确定输入的句子是否调用特定的动作，如果是这样，那么什么参数将被传递给动作的调用。

公开(公告)号：US09177553B1

公开(公告)日：2015-11-03

申请号：US13926943

申请日：2013-06-25

Applicant: Google Inc.

Inventor： Jakob D. Uszkoreit ,  Percy Liang ,  Daniel M. Bikel

IPC: G06F17/27 ,  G10L15/22

CPC classification number: G10L15/1822 ,  G06F17/27 ,  G06F17/2705 ,  G06F17/274 ,  G06F17/2785 ,  G10L15/22 ,  G10L2015/223

Abstract: A language processing system identifies first command input sentences that do not successfully parse by any parsing rule in a set of parsing rules. Each of the parsing rules is associated with an action, and a user device performs the action associated with a parsing rule in response to an input sentence being successfully parsed by the parsing rule. For each of these identified first sentences, the system determines whether the first input sentence has an underserving signal that is indicative of one or more actions being underserved. If the first sentence has the underserving signal, then the first sentence is selected as a candidate input sentence. Each candidate input sentence is provided to an action analysis processes that determines whether a candidate input sentence is to be associated with one action, and upon a positive determination generates a parsing rule for the candidate input sentence.

Abstract translation: 语言处理系统识别在一组解析规则中的任何解析规则无法成功解析的第一个命令输入句子。 解析规则中的每一个与动作相关联，并且用户设备响应于由解析规则成功解析的输入句子来执行与解析规则相关联的动作。 对于每个这些识别的第一句子，系统确定第一输入句是否具有指示一个或多个动作不足的不足的信号。 如果第一句话具有不良信号，则选择第一句作为候选输入句。 每个候选输入句被提供给动作分析处理，该动作分析处理确定候选输入句是否与一个动作相关联，并且在肯定确定时生成候选输入句的解析规则。