公开(公告)号：US20200302915A1

公开(公告)日：2020-09-24

申请号：US16889672

申请日：2020-06-01

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Amanda STENT ,  Srinivas BANGALORE

IPC: G10L15/06 ,  G10L15/08 ,  G10L15/183 ,  G06F40/12 ,  G06F40/137 ,  G10L15/22 ,  G10L15/00 ,  G10L15/04 ,  G10L25/12

Abstract: Disclosed herein are systems, computer-implemented methods, and computer-readable media for dialog modeling. The method includes receiving spoken dialogs annotated to indicate dialog acts and task/subtask information, parsing the spoken dialogs with a hierarchical, parse-based dialog model which operates incrementally from left to right and which only analyzes a preceding dialog context to generate parsed spoken dialogs, and constructing a functional task structure of the parsed spoken dialogs. The method can further either interpret user utterances with the functional task structure of the parsed spoken dialogs or plan system responses to user utterances with the functional task structure of the parsed spoken dialogs. The parse-based dialog model can be a shift-reduce model, a start-complete model, or a connection path model.

公开(公告)号：US20180261206A1

公开(公告)日：2018-09-13

申请号：US15980201

申请日：2018-05-15

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Amanda STENT ,  Srinivas BANGALORE

IPC: G10L15/06 ,  G10L15/08 ,  G06F17/22 ,  G10L15/00 ,  G10L25/12 ,  G10L15/22 ,  G10L15/183 ,  G10L15/04 ,  G10L15/18

Abstract: Disclosed herein are systems, computer-implemented methods, and computer-readable media for dialog modeling. The method includes receiving spoken dialogs annotated to indicate dialog acts and task/subtask information, parsing the spoken dialogs with a hierarchical, parse-based dialog model which operates incrementally from left to right and which only analyzes a preceding dialog context to generate parsed spoken dialogs, and constructing a functional task structure of the parsed spoken dialogs. The method can further either interpret user utterances with the functional task structure of the parsed spoken dialogs or plan system responses to user utterances with the functional task structure of the parsed spoken dialogs. The parse-based dialog model can be a shift-reduce model, a start-complete model, or a connection path model.

公开(公告)号：US20160151918A1

公开(公告)日：2016-06-02

申请号：US14557005

申请日：2014-12-01

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Svetlana STOYANCHEV ,  Srinivas BANGALORE ,  John CHEN ,  Hyuckchul JUNG

IPC: B25J13/00 ,  G06F17/27 ,  G06F17/28

CPC classification number: B25J13/003 ,  G06F17/2785

Abstract: A system, method and computer-readable storage devices are for processing natural language commands, such as commands to a robotic arm, using a Tag & Parse approach to semantic parsing. The system first assigns semantic tags to each word in a sentence and then parses the tag sequence into a semantic tree. The system can use statistical approach for tagging, parsing, and reference resolution. Each stage can produce multiple hypotheses, which are re-ranked using spatial validation. Then the system selects a most likely hypothesis after spatial validation, and generates or outputs a command. In the case of a robotic arm, the command is output in Robot Control Language (RCL).

Abstract translation: 系统，方法和计算机可读存储设备用于使用标签＆解析方法来处理自然语言命令，诸如对机器人手臂的命令。 系统首先为句子中的每个单词分配语义标签，然后将标签序列解析为语义树。 系统可以使用统计方法进行标记，解析和参考解析。 每个阶段都可以产生多个假设，这些假设使用空间验证进行重新排序。 然后，系统在空间验证之后选择最可能的假设，并生成或输出命令。 在机器人臂的情况下，命令以机器人控制语言（RCL）输出。

公开(公告)号：US20150339292A1

公开(公告)日：2015-11-26

申请号：US14797680

申请日：2015-07-13

Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

Inventor： Luciano De Andrade BARBOSA ,  Srinivas BANGALORE

IPC: G06F17/28 ,  G06F17/27

CPC classification number: G06F17/28 ,  G06F17/21 ,  G06F17/27 ,  G06F17/2705 ,  G06F17/2715 ,  G06F17/2735 ,  G06F17/2765 ,  G10L2015/0633

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for collecting web data in order to create diverse language models. A system configured to practice the method first crawls, such as via a crawler operating on a computing device, a set of documents in a network of interconnected devices according to a visitation policy, wherein the visitation policy is configured to focus on novelty regions for a current language model built from previous crawling cycles by crawling documents whose vocabulary considered likely to fill gaps in the current language model. A language model from a previous cycle can be used to guide the creation of a language model in the following cycle. The novelty regions can include documents with high perplexity values over the current language model.

Abstract translation: 本文公开了用于收集网络数据以便创建不同语言模型的系统，方法和非暂时的计算机可读存储介质。 被配置为实践该方法的系统首先通过根据访问策略的互连设备的网络中的诸如通过在计算设备上操作的爬行器来爬行一组文档，其中所述访问策略被配置为专注于新颖区域 目前的语言模型是从以前的爬行周期构建的，通过抓取其词汇被认为可能填补当前语言模型的空白的文档。 来自上一个循环的语言模型可用于指导在以下循环中创建语言模型。 新奇区域可以包括与当前语言模型相比具有高困惑价值的文档。

公开(公告)号：US20150134320A1

公开(公告)日：2015-05-14

申请号：US14080361

申请日：2013-11-14

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Vivek Kumar RANGARAJAN SRIDHAR ,  Srinivas BANGALORE ,  John CHEN

IPC: G06F17/28 ,  G10L15/00

CPC classification number: G10L15/005 ,  G06F17/2775 ,  G06F17/289 ,  G10L13/00 ,  G10L15/04 ,  G10L15/26

Abstract: A system, method and computer-readable storage device which balance latency and accuracy of machine translations by segmenting the speech upon locating a conjunction. The system, upon receiving speech, will buffer speech until a conjunction is detected. Upon detecting a conjunction, the speech received until that point is segmented. The system then continues performing speech recognition on the segment, searching for the next conjunction, while simultaneously initiating translation of the segment. Upon translating the segment, the system converts the translation to a speech output, allowing a user to hear an audible translation of the speech originally heard.

Abstract translation: 一种系统，方法和计算机可读存储设备，其通过在定位连接时分割语音来平衡机器翻译的等待时间和精度。 该系统在接收到语音时将缓冲语音，直到检测到连接。 在检测到连接时，直到该点被接收为止。 然后，系统继续在段上执行语音识别，搜索下一个连接，同时启动段的翻译。 在翻译片段时，系统将翻译转换为语音输出，允许用户听到原始听到的语音的可听翻译。

公开(公告)号：US20180001482A1

公开(公告)日：2018-01-04

申请号：US15705320

申请日：2017-09-15

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Svetlana STOYANCHEV ,  Srinivas BANGALORE ,  John CHEN ,  Hyuckchul JUNG

IPC: B25J13/00 ,  G06F17/27

CPC classification number: B25J13/003 ,  G06F17/2785

Abstract: A system, method and computer-readable storage devices are for processing natural language commands, such as commands to a robotic arm, using a Tag & Parse approach to semantic parsing. The system first assigns semantic tags to each word in a sentence and then parses the tag sequence into a semantic tree. The system can use statistical approach for tagging, parsing, and reference resolution. Each stage can produce multiple hypotheses, which are re-ranked using spatial validation. Then the system selects a most likely hypothesis after spatial validation, and generates or outputs a command. In the case of a robotic arm, the command is output in Robot Control Language (RCL).

公开(公告)号：US20170344665A1

公开(公告)日：2017-11-30

申请号：US15681741

申请日：2017-08-21

Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

Inventor： Srinivas BANGALORE ,  Junlan FENG ,  Michael J. JOHNSTON ,  Taniya MISHRA

IPC: G06F17/30

CPC classification number: G06F16/90332 ,  G06F16/23 ,  G06F16/907

Abstract: Extracting, from user activity data, quantitative attributes and qualitative attributes collected for users having user profiles. The quantitative attributes and the qualitative attributes are extracted during a specified time period determined before the user activity data is collected. Values for the quantitative attributes and the qualitative attributes are plotted, and subsets of the user profiles are clustered into separate group of users based on the plotted values. Delivering a product related content to the groups of users based on the clustering.

公开(公告)号：US20160328390A1

公开(公告)日：2016-11-10

申请号：US15212944

申请日：2016-07-18

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Luciano De Andrade BARBOSA ,  Srinivas BANGALORE

IPC: G06F17/28 ,  G06F17/21 ,  G06F17/27

CPC classification number: G06F17/28 ,  G06F17/21 ,  G06F17/27 ,  G06F17/2705 ,  G06F17/2715 ,  G06F17/2735 ,  G06F17/2765 ,  G10L2015/0633

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for collecting web data in order to create diverse language models. A system configured to practice the method first crawls, such as via a crawler operating on a computing device, a set of documents in a network of interconnected devices according to a visitation policy, wherein the visitation policy is configured to focus on novelty regions for a current language model built from previous crawling cycles by crawling documents whose vocabulary considered likely to fill gaps in the current language model. A language model from a previous cycle can be used to guide the creation of a language model in the following cycle. The novelty regions can include documents with high perplexity values over the current language model.

公开(公告)号：US20160004690A1

公开(公告)日：2016-01-07

申请号：US14853053

申请日：2015-09-14

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Srinivas BANGALORE ,  Sumit Chopra

IPC: G06F17/28

CPC classification number: G06F17/28

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for learning latent representations for natural language tasks. A system configured to practice the method analyzes, for a first natural language processing task, a first natural language corpus to generate a latent representation for words in the first corpus. Then the system analyzes, for a second natural language processing task, a second natural language corpus having a target word, and predicts a label for the target word based on the latent representation. In one variation, the target word is one or more word such as a rare word and/or a word not encountered in the first natural language corpus. The system can optionally assigning the label to the target word. The system can operate according to a connectionist model that includes a learnable linear mapping that maps each word in the first corpus to a low dimensional latent space.

Abstract translation: 本文公开了用于学习自然语言任务的潜在表示的系统，方法和非暂时的计算机可读存储介质。 一种被配置为练习该方法的系统，分析第一自然语言处理任务中的第一自然语言语料库以产生第一语料库中的单词的潜在表示。 然后，系统针对第二自然语言处理任务分析具有目标词的第二自然语言语料库，并且基于潜在表示来预测目标词的标签。 在一个变体中，目标词是一个或多个单词，例如在第一自然语言语料库中不遇到的罕见单词和/或单词。 系统可以选择将标签分配给目标字。 该系统可以根据连接主义模型来操作，该连接主义模型包括将第一语料库中的每个单词映射到低维空间的可学习的线性映射。

公开(公告)号：US20150379984A1

公开(公告)日：2015-12-31

申请号：US14845634

申请日：2015-09-04

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Amanda STENT ,  Srinivas BANGALORE

IPC: G10L15/06 ,  G10L15/04 ,  G10L15/00 ,  G10L25/12

CPC classification number: G10L15/063 ,  G06F17/22 ,  G06F17/2241 ,  G06F17/227 ,  G10L15/005 ,  G10L15/04 ,  G10L15/08 ,  G10L15/18 ,  G10L15/183 ,  G10L15/22 ,  G10L25/12 ,  G10L2015/0638

Abstract: Disclosed herein are systems, computer-implemented methods, and computer-readable media for dialog modeling. The method includes receiving spoken dialogs annotated to indicate dialog acts and task/subtask information, parsing the spoken dialogs with a hierarchical, parse-based dialog model which operates incrementally from left to right and which only analyzes a preceding dialog context to generate parsed spoken dialogs, and constructing a functional task structure of the parsed spoken dialogs. The method can further either interpret user utterances with the functional task structure of the parsed spoken dialogs or plan system responses to user utterances with the functional task structure of the parsed spoken dialogs. The parse-based dialog model can be a shift-reduce model, a start-complete model, or a connection path model.

Abstract translation: 本文公开了用于对话建模的系统，计算机实现的方法和计算机可读介质。 该方法包括接收注释以指示对话行为和任务/子任务信息的口头对话，用从层级，基于解析的对话模型解析口头对话，该对话模型从左向右逐渐操作，并且仅分析前一对话上下文以产生解析的口语对话 ，并构建解析的语音对话的功能任务结构。 该方法还可以用解析的口头对话的功能任务结构或用解析的口语对话的功能性任务结构对用户话语的计划系统响应来解释用户话语。 基于分析的对话模型可以是移位减少模型，起始完成模型或连接路径模型。