Abstract: According to implementations of the subject matter described herein, there is provided a solution for protein structure prediction. In this solution, a constraint set for a target protein is obtained, the constraint set comprising constraints for structural properties of the target protein. Feature information is extracted from the constraints respectively, and weights corresponding to the constraints are determined respectively based on the feature information of the constraints. Each weight indicates a degree of influence of the corresponding constraint in prediction of a structure of the target protein. The structure of the target protein is predicted based on the constraints in the constraint set and the weights. According to the solution, through the pre-processing on the constraints for use, it is possible to solve potential conflicts in the constraint set and eliminate constraint redundancy. This enables accurate prediction of the structure of the target protein.

Abstract: According to implementations of the present disclosure, a solution is proposed for protein structure prediction. In this solution, from a fragment library for a target protein, a plurality of fragments is determined for each of a plurality of residue positions of the target protein. Each fragment comprises a plurality of amino acid residues. Then, a feature representation of structures of the plurality of fragments is generated for the each residue position. Next, a prediction of at least one of a structure and a structural property of the target protein is determined based on the respective feature representations generated for the plurality of residue positions. In this way, the solution can leverage structural information of fragment libraries to complement and complete information used in protein structure prediction, and the accuracy of protein structure prediction is thus improved.

Abstract: A computing system is provided, including a processor configured to, during a training phase, provide a training data set including a pre-transformation molecular graph and post-transformation energy parameter value representing an energy change in a molecular system following an energy transformation. The pre-transformation molecular graph includes a plurality of normal nodes fully connected by edges. The processor is configured to encode structural information including a three-dimensional Euclidean distance along an edge connecting a pair of the normal nodes in each molecular graph as learnable embeddings. The processor is configured to input the training data set to a transformer-based graph neural network to train the network to perform an inference at inference time.

Abstract: A computing system is provided, including a processor configured to, during a training phase, provide a training data set, including a pre-transformation molecular graph and post-transformation energy parameter value representing an energy change in a molecular system following an energy transformation. The pre-transformation graph includes a plurality of normal nodes connected by edges representing a distance and a bond between a pair of the normal nodes. The processor is further configured to encode structural information in each pre-transformation molecular graph as learnable embeddings, the structural information describing the relative positions of the atoms represented by the normal nodes. The structural information includes an edge encoding representing a type of bond between a pair of normal nodes in each pre-transformation molecular graph, and a spatial encoding representing a shortest path distance along the edges between a pair of normal nodes in each pre-transformation molecular graph.

Abstract: Implementations of the subject matter described herein provide a solution for speech synthesis and speech recognition. In this solution, a Text to Speech (TTS) model and an Automatic Speech Recognition (ASR) model supporting at least one language are obtained. The TTS model and the ASR model are adjusted, based on a first set of paired data in a target language, to support the target language. The TTS model is optimized based on the first set of paired data and a first set of synthesized paired data in the target language generated by the ASR model while the ASR model is optimized based on the first set of paired data and a second set of synthesized paired data in the target language generated by the TTS model. As such, the solution can provide TTS and ASR models with high accuracy for languages lacking training data by using less training data.

Abstract: According to implementations of the subject matter described herein, a solution is proposed for super-resolution image reconstructing. According to the solution, an input image with first resolution is obtained. An invertible neural network is trained using the input image, wherein the invertible neural network is configured to generate an intermediate image with second resolution and first high-frequency information based on the input image, the second resolution being lower than the first resolution. Subsequently, an output image with third resolution is generated based on the input image and second high-frequency information by using an inverse network of the trained invertible neural network, the second high-frequency information conforming to a predetermined distribution, and the third resolution being higher than the first resolution. The solution can effectively process a low-resolution image obtained by an unknown downsampling method, thereby obtaining a high-quality and high-resolution image.

Abstract: According to implementations of the subject matter described herein, a solution for image rescaling is proposed. According to the solution, an input image of a first resolution is obtained. An output image of a second resolution and high-frequency information following a predetermined distribution are generated based on the input image by using a trained invertible neural network, where the first resolution exceeds the second resolution. Besides, a further input image of the second resolution is obtained. A further output image of the first resolution is generated based on the further input image and high-frequency information following the predetermined distribution by using an inverse network of the invertible neural network. This solution can downscale an original image into a visually-pleasing low-resolution image with the same semantics and also can reconstruct a high-resolution image of high quality from a low-resolution image.

Abstract: In implementations of the present disclosure, a solution for optimization of a learning network in an equivalent class space is provided. In this solution, base paths running through layers of a learning network are determined. Each node utilizes an activation function with a scaling invariant property to process an input from a node of a previous layer, each base path comprises a single node in each layer, and processing in the base paths is linearly independent from each other. A combined value of parameters associated with nodes in each base path is updated. A parameter associated with a node is used to adjust an input obtained from a node of a previous layer. Values of parameters associated with nodes in the base paths are updated based on updated combined values of parameters. Through this solution, optimization efficiency can be improved and more accurate optimized values of parameters are achieved.

Abstract: In implementations of the present disclosure, a solution for optimization of a learning network in an equivalent class space is provided. In this solution, base paths running through layers of a learning network are determined. Each node utilizes an activation function with a scaling invariant property to process an input from a node of a previous layer, each base path comprises a single node in each layer, and processing in the base paths is linearly independent from each other. A combined value of parameters associated with nodes in each base path is updated. A parameter associated with a node is used to adjust an input obtained from a node of a previous layer. Values of parameters associated with nodes in the base paths are updated based on updated combined values of parameters. Through this solution, optimization efficiency can be improved and more accurate optimized values of parameters are achieved.

Abstract: In some examples, a machine learning system may use morphological knowledge to enhance a deep learning framework for learning word embedding. The system may consider, among other things, morphological similarities between and among words in a learning process so as to handle new or rare words, edit distances, longest common substring similarities, morpheme similarities, and syllable similarities as morphological knowledge to build a relation matrix between or among words. The system may apply the deep learning framework to query classification, web search, text mining, information retrieval, and natural language processing tasks, for example. The system may accomplish such tasks with relatively high efficiency and speed, while utilizing less computing resources as compared to other systems.

Abstract: In implementations of the subject matter described herein, each token for containing an element in the training data is sampled according to a factorization strategy in training. Instead of using a single proposal, the property value of the target element located at the token being scanned is iteratively updated one or more times based on a combination of an element proposal and a context proposal. The element proposal tends to accept a value that is popular for the target element independently of the current piece of data, while the context proposal tends to accept whenever the property value that is popular in the context of the target data or popular for the element itself. The proposed modeling training approach can converge in a quite efficient way.

Abstract: Various implementations relate to asynchronous training of a machine learning model. A server receives feedback data generated by training the machine learning model from a worker. The feedback data are obtained by the worker with its own training data and are associated with previous values of a set of parameters of the machine learning model at the worker. The server determines differences between the previous values and current values of the set of parameters at the server. The current value may have been updated for once or more due to operation of other workers. Then, the server can update the current values of the set of parameters based on the feedback data and the differences between values of the set of parameters. Thus, the updating does not only take the training result of each worker into consideration but also makes proper compensation for delay between different workers.

Abstract: Many search engines attempt to understand and predict a user's search intent after the submission of search queries. Predicting search intent allows search engines to tailor search results to particular information needs of the user. Unfortunately, current techniques passively predict search intent after a query is submitted. Accordingly, one or more systems and/or techniques for actively predicting search intent from user browsing behavior data are disclosed herein. For example, search patterns of a user browsing a web page and shortly thereafter performing a query may be extracted from user browsing behavior. Queries within the search patterns may be ranked based upon a search trigger likelihood that content of the web page motivated the user to perform the query. In this way, query suggestions having a high search trigger likelihood and a diverse range of topics may be generated and/or presented to users of the web page.

Abstract: A chat engine is disclosed herein that can conduct emotionally intelligent chat conversations with client device users. User chat responses and surrounding environmental data are analyzed to respectively detect the user's emotional state and surrounding environments. A series of response selector components identify or generate possible chat responses to a user's chat statements based on the detected emotional states environment of the user. Emotionally intelligent chat responses are selected for presentation to a user based on calculated likelihoods that the responses will likely change or maintain the user's emotional state. Using the techniques disclosed herein, the chat engine tailors conversational responses to a user depending the user's detected emotional state.

Abstract: Techniques for determining user information needs and selecting data based on user information needs are described herein. The present disclosure describes extracting topics of interests to users from multiple sources including search log data and social network website, and assigns a budget to each topic to stipulate the quota of data to be selected for each topic. The present disclosure also describes calculating similarities between gathered data and the topics, and selecting top related data with each topic subject to limit of the budget. A search engine may use the techniques described here to select data for its index.

Abstract: In some examples, a machine learning system may use morphological knowledge to enhance a deep learning framework for learning word embedding. The system may consider, among other things, morphological similarities between and among words in a learning process so as to handle new or rare words, edit distances, longest common substring similarities, morpheme similarities, and syllable similarities as morphological knowledge to build a relation matrix between or among words. The system may apply the deep learning framework to query classification, web search, text mining, information retrieval, and natural language processing tasks, for example. The system may accomplish such tasks with relatively high efficiency and speed, while utilizing less computing resources as compared to other systems.

Abstract: In implementations of the subject matter described herein, each token for containing an element in the training data is sampled according to a factorization strategy in training. Instead of using a single proposal, the property value of the target element located at the token being scanned is iteratively updated one or more times based on a combination of an element proposal and a context proposal. The element proposal tends to accept a value that is popular for the target element independently of the current piece of data, while the context proposal tends to accept whenever the property value that is popular in the context of the target data or popular for the element itself. The proposed modeling training approach can converge in a quite efficient way.

Abstract: Systems and methods for responding to an advertisement request with a personalized advertisement are provided. More particularly, in response to an advertisement request from a requesting computer user, a plurality of candidate advertisements are identified and an advertisement is selected. A plurality of potential modifications for the selected advertisement are then identified. A modification, from the plurality of potential modifications, is selected as a function of a user preference vector associated with the requesting computer user. The user preference vector comprises a plurality of user preference items, each item indicating a likelihood of interaction of the requesting computer user with an advertisement having a modification according to a corresponding preference classification. Modification content corresponding to the selected modification is obtained and the modification content is added the selected advertisement.

Abstract: A method and system for augmenting a training set used to train a classifier of documents is provided. The augmentation system augments a training set with training data derived from features of documents based on a document hierarchy. The training data of the initial training set may be derived from the root documents of the hierarchies of documents. The augmentation system generates additional training data that includes an aggregate feature that represents the overall characteristics of a hierarchy of documents, rather than just the root document. After the training data is generated, the augmentation system augments the initial training set with the newly generated training data.

Abstract: Graph based evaluation by a computing device or system is described. In some example techniques, one or more subgraph nodes of a relationship subgraph may be generated based at least in part on a presenting of one or more items associated with the one or more associated subgraph nodes to a client. A click indication may be received that indicates the client has selected one of the presented items associated with the nodes. One or more edges of the relationship subgraph may be generated that begin at one or more respective unselected subgraph nodes associated with items presented concurrently with the selected item and end at a subgraph node associated with the selected item.