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: A knowledge graph processing method is provided. The method includes: selecting several nodes and their edges from a shared knowledge graph based on one or more entity types involved in a target service domain, to obtain a target subgraph, where the shared knowledge graph is obtained by fusing knowledge graphs of one or more service domains; processing the target subgraph to extract one or more graph features, where the graph feature includes some or all of the following: a node representation vector, an edge representation vector, a graph structure feature, a semantic feature of graph text information, and a graph rule feature; and providing the graph feature to a target data processing task of the target service domain, where the graph feature is used to serve as an input feature of the target data processing task together with a task customization feature.

Abstract: A method includes coarse clustering and secondary fine clustering. First, semantic vectors respectively corresponding to a plurality of texts are determined by using a semantic representation model, and a similarity matrix between the plurality of texts is determined based on the semantic vectors of the plurality of texts. Next, in a coarse clustering phase, M similar texts with maximum similarities respectively corresponding to the plurality of texts are determined from the similarity matrix, and the corresponding texts are used as selected central texts when the similarities corresponding to the M similar texts are greater than a threshold, to quickly remove a large amount of isolated noise. Then, candidate class clusters are obtained based on data corresponding to the central texts in the similarity matrix, candidate class clusters with a cross-text are combined, and then secondary fine clustering is performed on a combined class cluster.

Abstract: The present application discloses an event extraction method and apparatus, a computer program product, a storage medium, and a device.

Abstract: Implementations of the present specification disclose a knowledge graph reasoning method and apparatus, a model training method and apparatus, and a computer device. The method includes: obtaining a query entity and a query relationship; selecting one or more nearest neighbor entities of the query entity from a knowledge graph; determining a first probability of a nearest neighbor entity of the one or more nearest neighbor entities, where the first probability is used to indicate a possibility that the nearest neighbor entity is in communication with the query relationship; selecting a nearest neighbor entity of the one or more nearest neighbor entities as a candidate entity based on the first probability; and selecting a candidate entity matching the query entity and the query relationship as a result entity. In the implementations of the present specification, the efficiency of knowledge graph reasoning can be improved.

Abstract: Described herein are methods of making the visible light photocatalysts without the use of templates that can comprise: (1) mixing a metal precursor, an alcohol, and a solvent to form a self assembled shapes at a temperature between the freezing point of the solvent and the boiling point of the solvent, (2) strengthening the shapes at a temperature of about 35° C. to about 300° C. for about 30 minutes to about 96 hours, and then (3) annealing the shapes at a temperature of between about 450° C. to about 750° C. for between about 4 hours to about 16 hours in a gaseous atmosphere. Also described are photocatalysts created by the described methods.

Abstract: Embodiments of the present specification disclose a method, an apparatus, a system, a device, and a storage medium for answering user questions, including: obtaining a user question; encoding the user question and a schema level of pre-constructed structured data to obtain a first feature vector, wherein the structured data further comprises a data level, wherein the data level comprises knowledge for answering questions structured according to the schema level; retrieving one or more candidate sub-graphs related to the user question from the structured data; encoding the one or more candidate sub-graphs to obtain a second feature vector; performing multi-task classification for the user question based on the first feature vector and the second feature vector; and obtaining answer content for the user question based on a result of the multi-task classification.

Abstract: Embodiments of the present specification disclose a method, an apparatus, a system, a device, and a storage medium for answering user questions, including: obtaining a user question; encoding the user question and a schema level of pre-constructed structured data to obtain a first feature vector, wherein the structured data further comprises a data level, wherein the data level comprises knowledge for answering questions structured according to the schema level; retrieving one or more candidate sub-graphs related to the user question from the structured data; encoding the one or more candidate sub-graphs to obtain a second feature vector; performing multi-task classification for the user question based on the first feature vector and the second feature vector; and obtaining answer content for the user question based on a result of the multi-task classification.

Abstract: Implementations of this disclosure provide methods and apparatuses for generating recommendation information. An example method includes matching text content from a text content library based on a plurality of predetermined scenario-related words; extracting keywords from the related text content, to generate a plurality of training samples; and for each training sample, providing a source sequence of a sequence pair corresponding to the training sample as an input to a recommendation information generation model, obtaining, from the recommendation information generation model, a predicted word, and adjusting a model parameter of the recommendation information generation model based on a comparison between the predicted word and a corresponding word in a target sequence of the sequence pair corresponding to the training sample, to train the recommendation information generation model.

Abstract: Implementations of this disclosure provide methods and apparatuses for generating recommendation information. An example method includes matching text content from a text content library based on a plurality of predetermined scenario-related words; extracting keywords from the related text content, to generate a plurality of training samples; and for each training sample, providing a source sequence of a sequence pair corresponding to the training sample as an input to a recommendation information generation model, obtaining, from the recommendation information generation model, a predicted word, and adjusting a model parameter of the recommendation information generation model based on a comparison between the predicted word and a corresponding word in a target sequence of the sequence pair corresponding to the training sample, to train the recommendation information generation model.

Abstract: Described herein are methods of making the visible light photocatalysts without the use of templates that can comprise: (1) mixing a metal precursor, an alcohol, and a solvent to form a self assembled shapes at a temperature between the freezing point of the solvent and the boiling point of the solvent, (2) strengthening the shapes at a temperature of about 35° C. to about 300° C. for about 30 minutes to about 96 hours, and then (3) annealing the shapes at a temperature of between about 450° C. to about 750° C. for between about 4 hours to about 16 hours in a gaseous atmosphere. Also described are photocatalysts created by the described methods.

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: 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: 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: 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.

Abstract: Some implementations provide techniques for selecting web pages for inclusion in an index. For example, some implementations apply regularization to select a subset of the crawled web pages for indexing based on link relationships between the crawled web pages, features extracted from the crawled web pages, and user behavior information determined for at least some of the crawled web pages. Further, in some implementations, the user behavior information may be used to sort a training set of crawled web pages into a plurality of labeled groups. The labeled groups may be represented in a directed graph that indicates relative priorities for being selected for indexing.

Abstract: Implementations for providing menu-based advertising are disclosed. A search engine front-end determines non-search engine information pages that are relevant to the user input based on user input entered into a search query field on a search page. A suggestion menu is caused to be displayed on a search page. The suggestion menu includes interactive elements that are interactive to cause a client device to retrieve the non-search engine information pages associated with the interactive elements. The interactive elements may be advertisements, and the suggestion menu may also be used to display search query suggestions.

Abstract: A task guidance tool that displays instructional steps and associated advertisements may facilitate the accomplishment of a task by users who are otherwise unfamiliar with the task. The task guidance tool may be developed from input data mined from various sources. The task guidance tool may display a series of step pages in which each step page include instructions for accomplishing a corresponding step of the task. Further, one or more step pages of the task guidance tool may be provided with selected advertisements that are displayed with the step instructions.

Abstract: An advertisement perception predictor may forecast the effectiveness of an online advertisement in a web page by predicting whether the online advertisement may be perceived by a consumer. The advertisement perception predictor may use a perception model that is trained for determining perception probability values of online advertisements. The perception model may be applied to an online advertisement to determine a perception probability value for the online advertisement. The perception probability value may indicate the likelihood that a consumer is likely to view the online advertisement.

Abstract: Efficient search query clustering using tripartite graphs may enable a search engine developer to model information needs of users while expending less computing resources. The efficient clustering of search queries may involve multiple computing devices receiving a subgraph of a multi-partite graph that encompasses search queries, as well as receiving a global center vector table that includes cluster center entries for query clusters. At each computing device, the received global center vector table may be filtered to eliminate one or more cluster center entries that are irrelevant to the search queries. Subsequently, the search queries may be clustered into the query clusters by at least using the filtered global center vector table at each of the computing devices. In some instances, one or more comparisons between search queries and the cluster center entries in the global center vector table during the clustering may be eliminated.