Polyai Limited

Digital Genius Limited

Polyal Limited

Samuel John Coope

Tsung-Hsien Wen

Pei-Hao Su

Nikola Mrksic

Ivan Vulic

Matthew Steedman Henderson

Benjamin Peter Levin

Inigo Casanueva Perez

Emmanuel Sevrin

Yoram Bachrach

Pawel Budzianowski

Conan McMurtrie

Razvan-Emanuel Kusztos

Bohdan Maksak

Ivan Vulić

Ho Man Yau

Qian Zheng

Georgios Spithourakis

Daniela Susanne Gerz

Swaroop Jagadeesh

Andrej Zukov Gregoric

Jose Marcos Rodríguez Fernández

Kacper Jakub Zylka

Pavel Minkovsky

Kacper Jakub Żyłka

Nikola Mrksić

Vincent Yohann Dollet

Catherine Rachel Oxley

Andrej Zukov Gregorc

I{circumflex Over (n)}igo Casanueva Perez

Duong Hà Anh Nguyên

Joshua Luke Jeffries Hook

Paul Julian Annetts

A dialogue system, comprising: a first input configured to obtain first input data relating to speech or text provided by a user through a first interface; a first output configured to provide first output data relating to speech or text information specified by a determined dialogue act through the first interface; one or more processors, configured to: receive second input data through a second interface; store information specifying one or more configuration settings based on the second input data; and perform a dialogue method using a dialogue platform, the dialogue method comprising: determining dialogue information from the first input data; determining a dialogue act based on the determined dialogue information using a dialogue management module, wherein determining the dialogue act comprises selecting a next state from a plurality of states stored in the dialogue management module, wherein at least some of the plurality of states comprise information specifying a dialogue act and at least some of the plurality of states comprise transition information specifying a transition to another state, the transitions defining one or more dialogue pathways, wherein selecting the next state comprises selecting a state which is specified by the transition information in a current state or selecting a state which is specified by a rule in a first set of one or more rules, wherein at least one of the plurality of states comprises stored information specifying a configuration setting based on the second input data; updating a configuration of the dialogue platform for the next user input when the selected next state comprises stored information specifying a configuration setting. See FIG.().

Dialogue configuration system and method

A method of obtaining a response to a query inputted by a user, the method comprising: receiving a user inputted query; representing the user inputted query as a sequence of embedding vectors using a first model; encoding the sequence of embedding vectors to produce a context vector using a second model; retrieving responses with associated response vectors; scoring response vectors against the context vector, wherein the scoring is a measure of the similarity between the context vector and a response vector; and outputting the responses with the closest response vectors, wherein the first model is configured to segment a user inputted query into a sequence of units from a vocabulary of units and represent each unit in the sequence as an embedding vector, wherein at least one of the units in the vocabulary is an incomplete word, and wherein the first model comprises parameters that are stored using eight bits per parameter; and wherein the second model has been trained using corresponding queries and responses such that an encoding is used that maximises the similarity between the response vector and context vector for a corresponding query and response.

Dialogue system, a method of obtaining a response from a dialogue system, and a method of training a dialogue system

Systems and methods for conversing with a user

A method of obtaining a response to a query inputted by a user, the method comprising:

Response retrieval system and method

Certain examples described herein provide methods and systems for implementing a conversational agent, e.g. to train a predictive model used by the conversational agent. In examples, text data representing agent messages from a dialogue database are clustered and the clusters are used to generate response templates for use by the conversational agent. The predictive model is trained on training data generated by selectively assigning response templates to agent messages from text dialogues. Examples enable a predictive model to be trained on high quality data sets that are generated automatically from a corpus of historical data. In turn, they enable a natural language interface to be efficiently provided.

Conversational agent

Certain examples are described that provide methods and systems for generating templates for use by a conversational agent. These examples enable a natural language interface to be provided. Certain examples cluster user and agent messages from a corpus of text data representing text dialogues. This clustering enables response templates to be generated in a way that takes into account a context in which responses are given. In certain examples, messages that are exchanged between a user and a conversational agent are embedded as numeric arrays based a neural sequence-to-sequence model. Clustering routines are used to group dialogue encodings into one or more response clusters, and these clusters may then be used to generate response templates. The response templates may be used by a conversational agent to prepare a response to a user message.

Template generation for a conversational agent

Growing community of inventors

London, United Kingdom

Samuel John Coope