公开(公告)号：WO2017168246A1

公开(公告)日：2017-10-05

申请号：PCT/IB2017/000411

申请日：2017-03-29

Applicant: MALUUBA INC.

Inventor： SCHULZ, Hannes ,  HE, Jing

IPC: G10L15/22 ,  G06F17/27 ,  G10L15/16

CPC classification number: G10L15/22 ,  G10L13/08 ,  G10L15/16 ,  G10L15/197 ,  G10L15/265 ,  G10L25/30 ,  G10L2015/223

Abstract: Described herein are systems and methods for providing hierarchical state tracking in a spoken dialogue system. A sequence of turns is received by a spoken dialogue system. Each turn includes a user utterance and a machine act. At each turn, a value pointer and a turn pointer are provided for that turn. The value pointer represents a probability distribution over the one or more words in the user utterance that indicates whether each word in the user utterance is a slot value for a slot. The turn pointer identifies which turn in a set of turns includes a currently-relevant slot value for the slot, where the set of turns includes a current turn for which the turn point is being provided, and all turns that precede the current turn.

Abstract translation: 这里描述的是用于在口头对话系统中提供分级状态跟踪的系统和方法。 口头对话系统接收一系列转弯。 每一转都包括用户话语和机器动作。 在每一回合中，为该回合提供值指针和转向指针。 值指针表示对用户话语中的一个或多个单词的概率分布，其指示用户话语中的每个单词是否是时隙的时隙值。 转弯指针标识一组转弯中的哪一匝包括该槽的当前相关的槽值，其中转弯组包括转弯点正被提供的当前转弯以及当前转弯之前的所有转弯。 / p>

公开(公告)号：WO2017210613A1

公开(公告)日：2017-12-07

申请号：PCT/US2017/035767

申请日：2017-06-02

Applicant: MALUUBA INC.

Inventor： SHARMA, Shikhar ,  HE, Jing ,  SULEMAN, Kaheer ,  BACHMAN, Philip ,  SCHULZ, Hannes

IPC: G06F17/28

Abstract: Described herein are systems and methods for providing a natural language generator in a spoken dialogue system that considers both lexicalized and delexicalized dialogue act slot-value pairs when translating one or more dialogue act slot-value pairs into a natural language output. Each slot and value associated with the slot in a dialogue act are represented as (dialogue act + slot, value), where the first term (dialogue act + slot) is delexicalized and the second term (value) is lexicalized. Each dialogue act slot-value representation is processed to produce to produce at least one delexicalized sentence as an output. A lexicalized sentence is produced by replacing each delexicalized slot with the value associated with the delexicalized slot.

Abstract translation: 这里描述的是用于在口述对话系统中提供自然语言生成器的系统和方法，该系统和方法在将一个或多个对话动作时隙 - 值对转换为一个或多个对话动作时隙值对时考虑了词汇化和非动词化对话两者 自然语言输出。 与对话动作中的时隙相关联的每个时隙和值被表示为（对话动作+时隙，值），其中第一项（对话动作+时隙）被去灵活化并且第二项（值）被词汇化。 每个对话行为时隙值表示被处理以产生至少一个作为输出的delexicalized句子。 一个词汇化的句子是通过用与delexicalized插槽关联的值替换每个delexicalized插槽来生成的。

公开(公告)号：WO2017197330A1

公开(公告)日：2017-11-16

申请号：PCT/US2017/032512

申请日：2017-05-12

Applicant: MALUUBA INC.

Inventor： FATEMI BOOSHEHRI, Seyed Mehdi ,  EL ASRI, Layla ,  SCHULZ, Hannes ,  HE, Jing ,  SULEMAN, Kaheer

IPC: G06F3/16 ,  G10L15/22 ,  G06N3/04

Abstract: Described herein are systems and methods for two-stage training of a spoken dialogue system. The first stage trains a policy network using external data to produce a semi-trained policy network. The external data includes one or more known fixed dialogues. The second stage trains the semi-trained policy network through interaction to produce a trained policy network. The interaction may be interaction with a user simulator.

Abstract translation: 这里描述的是用于口头对话系统的两阶段训练的系统和方法。 第一阶段使用外部数据训练一个策略网络，以产生一个半训练的策略网络。 外部数据包括一个或多个已知的固定对话。 第二阶段通过互动训练半训练的政策网络，建立训练有素的政策网络。 交互可以是与用户模拟器的交互。