Abstract: 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

Abstract: 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 response

Abstract: A system comprising: an input configured to receive input speech data originating from a user; an output configured to output speech or text information; and a processor configured to: provide first input data to a character sequence determination module to determine a character sequence from the first input data, wherein determining a character sequence comprises: obtaining a first list of one or more candidate character sequences from the first input data; selecting a first candidate character sequence from the first list; generating a first confirm request to confirm the selected first candidate character sequence, wherein the first confirm request is outputted by way of the output; if second input data indicating that the first candidate character sequence is not confirmed is received, selecting a second candidate character sequence and generating a second confirm request to confirm the selected second candidate if the second candidate character sequence is different from the first candidate character s

Abstract: A system comprising: an input configured to receive input speech data originating from a user; an output configured to output speech or text information; and a processor configured to: provide first input data to a character sequence determination module to determine a character sequence from the first input data, wherein determining a character sequence comprises: obtaining a first list of one or more candidate character sequences from the first input data; selecting a first candidate character sequence from the first list; generating a first confirm request to confirm the selected first candidate character sequence, wherein the first confirm request is outputted by way of the output; if second input data indicating that the first candidate character sequence is not confirmed is received, selecting a second candidate character sequence and generating a second confirm request to confirm the selected second candidate if the second candidate character sequence is different from the first candidate character s

Abstract: 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 response

Abstract: A system comprising: an input configured to receive input speech data originating from a user; an output configured to output speech or text information; and a processor configured to: provide first input data to a character sequence determination module to determine a character sequence from the first input data, wherein determining a character sequence comprises: obtaining a first list of one or more candidate character sequences from the first input data; selecting a first candidate character sequence from the first list; generating a first confirm request to confirm the selected first candidate character sequence, wherein the first confirm request is outputted by way of the output; if second input data indicating that the first candidate character sequence is not confirmed is received, selecting a second candidate character sequence and generating a second confirm request to confirm the selected second candidate if the second candidate character sequence is different from the first candidate character s

Abstract: A method of obtaining a response to a query inputted by a user, the method comprising: receiving a user inputted query; encoding said query to produce a context vector; retrieving responses with associated response vectors; scoring response vectors in the database 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 encoding said query to produce a context vector comprises using a pre-trained model, wherein said pre-trained 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: Certain examples described herein allow feedback to be exchanged between a conversational agent and an operator (so-called “bi-directional” feedback). Certain examples allow an incorrect response template to be indicated by the operator and the conversational agent to compute a contribution for tokens representative of how influential the tokens were in the prediction of the incorrect response template by an applied predictive model. The computed contribution is used to provide further feedback to the operator comprising potential tokens to disassociate with the incorrect response template. The operator then selects the tokens they wish to disassociate and the parameters of the predictive model are adjusted based on this feedback. By repeating this process, an accuracy of a conversational agent, in the form of the response templates that are selectable for a text dialogue, may be improved.

Abstract: 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.