Babylon Partners Limited

Nils Yannick Hammerla

Pietro Cavallo

Dane Grant Sherburn

Francesco Moramarco

Daniel William Busbridge

April Tuesday Shen

Olufemi Awomosu

Jack Flann

Vitalii Zhelezniak

Aleksandar Savkov

Alexsandar Savkov

Francisco Vargas

Kamen Brestnichki

A graphical classification method for classifying graphical structures, said graphical structures comprising nodes defined by feature vectors and having relations between the nodes. The method includes representing the feature vectors and relations as a first graphical representation. The method also includes mapping said first graphical representation into a second graphical representation wherein the mapping comprises using an attention mechanism, said attention mechanism establishes the importance of specific feature vectors dependent on their neighbourhood and the relations between the feature vectors, said mapping transforming the feature vectors of the first graphical representation to transformed feature vectors in the second graphical representation. The method also includes combining the transformed feature vectors to obtain a third combined representation said third combined representation being an indication of the classification of the graphical structure.

Method and system for extracting information from graphs

A computer implemented method for classifying molecular structures is provided. The method includes representing the elements and atoms in a molecular structure as nodes and the bonds as relations as a first graphical representation. The method also includes mapping said first graphical representation into a second graphical representation wherein the mapping comprises using an attention mechanism, said attention mechanism establishes the importance of specific feature vectors dependent on their neighbourhood and the relations between the feature vectors, said mapping transforming the feature vectors of the first graphical representation to transformed feature vectors in the second graphical representation. The method also includes combining the transformed feature vectors to obtain a third combined representation. The method also includes mapping said third combined representation to a feature vector indicating properties of the molecular structure.

A method of training a model, said model being adapted to map a first graphical data structure representation to a second graphical data structure representation, the first graphical data structure representation comprising nodes, with at least one of a plurality of relations between said nodes, the second graphical data structure representation comprising nodes, the mapping comprises using an attention mechanism, wherein said attention mechanism establishes the importance of specific nodes dependent on their neighbourhood and the relations between the nodes, wherein the mapping comprising using a projection kernel to map the nodes of the first graphical structure to nodes of an intermediate representation and using an attention kernel to enact the attention mechanism. The method includes receiving a training data set comprising an output layer and a corresponding input layer. The method also includes training the parameters of the projection kernel and the attention kernel using the training data set.

Methods for determining whether two sets of words are similar are provided. In one aspect, a method includes receiving a first set of words and a second set of words, whichare subsets of a vocabulary, and each of the first and second sets of words include word embeddings corresponding to each word. The method also includes determining a word membership function for each word in the vocabulary. Determining the word membership includes determining a set of similarity values, each representing the similarity between the word and a respective word in the vocabulary. The method also includes determining a membership function for the first and second sets of words based on the determined word membership functions, and determining a set-based coefficient for the similarity between the first and second sets of words based on the membership function. Systems and devices are also provided.

Device and method for natural language processing

A method of mapping a first graphical data structure representation to a second graphical data structure representation, the first graphical data structure representation comprising nodes, with at least one of a plurality of relations between said nodes, the second graphical data structure representation comprising nodes, the mapping comprises using an attention mechanism, wherein said attention mechanism establishes the importance of specific nodes dependent on their neighbourhood and the relations between the nodes.

Embodiments described herein provide a more flexible, effective, and computationally efficient means for determining multiple intents within a natural language input. Some methods rely on specifically trained machine learning classifiers to determine multiple intents within a natural language input. These classifiers require a large amount of labelled training data in order to work effectively, and are generally only applicable to determining specific types of intents (e.g., a specifically selected set of potential inputs). In contrast, the embodiments described herein avoid the use of specifically trained classifiers by determining inferred clauses from a semantic graph of the input. This allows the methods described herein to function more efficiently and over a wider variety of potential inputs.

Semantic graph traversal for recognition of inferred clauses within natural language inputs

The disclosed system addresses a technical problem tied to computer technology and arising in the realm of computer memory capacity, namely the technical problem of providing a flexible response dialogue system that can be utilised for a variety of different types of dialogue without requiring the system to be specifically trained for each situation. This therefore avoids the need for large amounts of labelled training data for each type of dialogue (each potential conversation flow or subject area for the conversation). The disclosed system solves this technical problem by using semantic similarity to match a user's input to one of a set of predefined inputs (predefined user responses). Various mechanisms are implemented to provide disambiguation in the event of multiple potential matches for the input. By using semantic similarity, the user's response in unconstrained. This therefore provides a user interface that is more user-friendly.

Flexible-response dialogue system through analysis of semantic textual similarity

A computer-implemented method comprising: receiving the first set of words and the second set of words, wherein each of the first and second sets of words; calculating a first likelihood-based measure representing how well a first model can be fit to the first and second sets of words, the first model comprising a shared parametric distribution representing both the first and second sets of words; calculating a second likelihood-based measure representing how well a second model can be fit to the first and second sets of words, the second model comprising a first parametric distribution representing the first set of words and a second parametric distribution representing the second set of words; calculating a similarity score based on a ratio of the first likelihood measure to the second likelihood measure, the similarity score being representative of the similarity between the first and second sets of words; and outputting the similarity score.

Growing community of inventors

London, United Kingdom

Nils Yannick Hammerla