Patents by Inventor Matthew Steedman Henderson
Matthew Steedman Henderson has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11741109Abstract: 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 responseType: GrantFiled: December 10, 2019Date of Patent: August 29, 2023Assignee: PolyAI LimitedInventors: Ivan Vulic, Matthew Steedman Henderson, Pei-Hao Su, Tsung-Hsien Wen, Inigo Casanueva Perez, Nikola Mrksic, Samuel John Coope
-
Patent number: 11210306Abstract: 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 responseType: GrantFiled: December 30, 2020Date of Patent: December 28, 2021Assignee: PolyAI LimitedInventors: Matthew Steedman Henderson, Pei-Hao Su, Tsung-Hsien Wen, Inigo Casanueva Perez, Nikola Mrksic, Samuel John Coope, Ivan Vulic
-
Patent number: 11132988Abstract: A computer implemented method comprising: receiving input data relating to a speech or text signal originating from a user; representing the input data as a first sequence of first representations, each representing a unit of the input data; representing the input data as a second sequence of second representations, each representing one of the units of the input data; using a model to determine a tag sequence from the first sequence of first representations, wherein the model comprises an attention layer using the second sequence of second representations, wherein the tag sequence comprises one or more tags from a set of tags comprising a first tag; if one or more units of the input data correspond to the first tag, determining a system dialogue act based on the part of the input data corresponding to the first tag; and outputting speech or text information specified by the determined dialogue act.Type: GrantFiled: October 22, 2020Date of Patent: September 28, 2021Assignee: PolyAI LimitedInventors: Matthew Steedman Henderson, Pei-Hao Su, Tsung-Hsien Wen, Inigo Casanueva Perez, Nikola Mrksic, Ivan Vulic
-
Publication number: 20210141798Abstract: 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 responseType: ApplicationFiled: December 10, 2019Publication date: May 13, 2021Inventor: Matthew Steedman Henderson
-
Publication number: 20210141799Abstract: 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 responseType: ApplicationFiled: December 30, 2020Publication date: May 13, 2021Inventor: Matthew Steedman Henderson
-
Patent number: 10885906Abstract: A dialogue system comprising: an input for receiving input data relating to a speech or text signal originating from a user; an output for outputting speech or text information specified by a dialogue act; and a processor configured to: generate features from the input signal; for each of a plurality of classifier models, each classifier model corresponding to a dialogue slot, and for one or more values corresponding to the dialogue slot, input features generated from the input signal, the classifier model outputting a probability corresponding to each of three or more relations, wherein the relations specify the relation of the value to the dialogue slot; update a belief state based on the outputs of the classifier models; determine a system dialogue act by inputting information relating to the belief state into a policy model; output speech or text information specified by the determined dialogue act at the output.Type: GrantFiled: November 8, 2019Date of Patent: January 5, 2021Assignee: PolyAI LimitedInventors: Matthew Steedman Henderson, Tsung-Hsien Wen, Pei-Hao Su, Nikola Mrksic, Ivan Vulic
-
Patent number: 10847141Abstract: A dialogue system comprising: an input for receiving input data relating to a speech or text signal originating from a user; an output for outputting speech or text information specified by a dialogue act; and a processor configured to: update a belief state, the belief state comprising information corresponding to one or more dialogue options, each dialogue option comprising a slot and a corresponding slot value, based on the input signal; determine a dialogue act, wherein a dialogue act is determined by applying one or more rules to world state information, the world state comprising information relating to the dialogue, wherein rules are applied in two or more ordered stages for each dialogue turn, wherein one of the stages is a first update stage, comprising applying one or more further rules controlling updating of the world state information based on the belief state information, and another of the stages is an act selection stage, comprising determining the dialogue act by applying the one or more ruleType: GrantFiled: November 8, 2019Date of Patent: November 24, 2020Assignee: PolyAI LimitedInventors: Matthew Steedman Henderson, Tsung-Hsien Wen, Pei-Hao Su, Nikola Mrksic, Ivan Vulic, Inigo Casanueva-Perez
-
Patent number: 10664527Abstract: 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.Type: GrantFiled: January 18, 2019Date of Patent: May 26, 2020Assignee: PolyAI LimitedInventors: Matthew Steedman Henderson, Pei-Hao Su, Nikola Mrksic, Tsung-Hsien Wen, Inigo Casanueva Perez, Ivan Vulic, Georgios Spithourakis, Samuel John Coope, Pawel Budzianowski, Daniela Susanne Gerz
-
Publication number: 20200152184Abstract: A dialogue system comprising: an input for receiving input data relating to a speech or text signal originating from a user; an output for outputting speech or text information specified by a dialogue act; and a processor configured to: generate features from the input signal; for each of a plurality of classifier models, each classifier model corresponding to a dialogue slot, and for one or more values corresponding to the dialogue slot, input features generated from the input signal, the classifier model outputting a probability corresponding to each of three or more relations, wherein the relations specify the relation of the value to the dialogue slot; update a belief state based on the outputs of the classifier models; determine a system dialogue act by inputting information relating to the belief state into a policy model; output speech or text information specified by the determined dialogue act at the output.Type: ApplicationFiled: November 8, 2019Publication date: May 14, 2020Inventors: Matthew Steedman Henderson, Tsung-Hsien Wen, Pei-Hao Su, Nikola Mrksic, Ivan Vulic
-
Publication number: 20200152182Abstract: A dialogue system comprising: an input for receiving input data relating to a speech or text signal originating from a user; an output for outputting speech or text information specified by a dialogue act; and a processor configured to: update a belief state, the belief state comprising information corresponding to one or more dialogue options, each dialogue option comprising a slot and a corresponding slot value, based on the input signal; determine a dialogue act, wherein a dialogue act is determined by applying one or more rules to world state information, the world state comprising information relating to the dialogue, wherein rules are applied in two or more ordered stages for each dialogue turn, wherein one of the stages is a first update stage, comprising applying one or more further rules controlling updating of the world state information based on the belief state information, and another of the stages is an act selection stage, comprising determining the dialogue act by applying the one or more ruleType: ApplicationFiled: November 8, 2019Publication date: May 14, 2020Inventors: Matthew Steedman Henderson, Tsung-Hsien Wen, Pei-Hao Su, Nikola Mrksic, Ivan Vulic, Inigo Casanueva-Perez
-
Patent number: 10083157Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for transforming and classifying text based on analysis of training texts from particular authors. One of the methods includes receiving an input text including one or more words and a requested author; generating a vector stream representing the input text based on an encoder language model and including one or more multi-dimensional vectors associated with associated words of the words of the input text and representing a distribution of contexts in which the associated words occurred in a plurality of training texts; and producing an output text representing a particular transformation of the input text based at least in part on a decoder language model, the generated vector stream, and the requested author.Type: GrantFiled: August 5, 2016Date of Patent: September 25, 2018Assignee: Google LLCInventors: Brian Patrick Strope, Matthew Steedman Henderson
-
Publication number: 20170039174Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for transforming and classifying text based on analysis of training texts from particular authors. One of the methods includes receiving an input text including one or more words and a requested author; generating a vector stream representing the input text based on an encoder language model and including one or more multi-dimensional vectors associated with associated words of the words of the input text and representing a distribution of contexts in which the associated words occurred in a plurality of training texts; and producing an output text representing a particular transformation of the input text based at least in part on a decoder language model, the generated vector stream, and the requested author.Type: ApplicationFiled: August 5, 2016Publication date: February 9, 2017Inventors: Brian Patrick Strope, Matthew Steedman Henderson