Abstract: A computing device receives a message including a request for a recommendation. A representation of a hypothetical ideal recommendation to provide in response to the message is determined based on the message content. Data regarding entities that are potential recommendations are retrieved from a data store, the data regarding each entity including a representation of the entity (e.g., a vector) derived from factual information about the entity and opinions of other users of the entity. Ranking scores are determined for at least a subset of the entities based on the difference between the entity representations and the representation of the hypothetical ideal recommendation. An entity to recommend is selected based on the ranking scores and a reply to the message is sent that identifies the selected entity.

Abstract: A user interacts with a virtual digital assistant with the intent that it provides assistance with a task. The user sends messages to the virtual digital assistant that include content obtained via user input at a client device. An intent determination model is applied to the content to identify the user's intent. The virtual digital assistant identifies agents that are capable of servicing the intent are identified and retrieves contextual data relating to the message from a data store. An intent arbitration model is used to select one of the agents which is activated to provide assistance with the task. The contextual information may include global metrics of agent performance and/or information regarding the user's preferences.

Abstract: An online system receives a request to generate presentation content for presentation to a user. The online system receives a set of content items and identifies a surface for presenting the presentation information to the user. For example, the surface may be a voice only surface, a voice and graphical display, a graphical display only. Based on the identified surface, the online system ranks the set of content items. The online system then determines presentation information for a subset of the content items and transmits instructions to present the presentation information at the surface.

Abstract: The customization of language modeling components for speech recognition is provided. A list of language modeling components may be made available by a computing device. A hint may then be sent to a recognition service provider for combining the multiple language modeling components from the list. The hint may be based on a number of different domains. A customized combination of the language modeling components based on the hint may then be received from the recognition service provider.

Abstract: An online system receives a request to generate presentation content for presentation to a user. The online system receives a set of content items and identifies a surface for presenting the presentation information to the user. For example, the surface may be a voice only surface, a voice and graphical display, a graphical display only. Based on the identified surface, the online system ranks the set of content items. The online system then determines presentation information for a subset of the content items and transmits instructions to present the presentation information at the surface.

Abstract: A computing device receives a message including a request for a recommendation. A representation of a hypothetical ideal recommendation to provide in response to the message is determined based on the message content. Data regarding entities that are potential recommendations are retrieved from a data store, the data regarding each entity including a representation of the entity (e.g., a vector) derived from factual information about the entity and opinions of other users of the entity. Ranking scores are determined for at least a subset of the entities based on the difference between the entity representations and the representation of the hypothetical ideal recommendation. An entity to recommend is selected based on the ranking scores and a reply to the message is sent that identifies the selected entity.

Abstract: A user interacts with a virtual digital assistant with the intent that it provides assistance with a task. The user sends messages to the virtual digital assistant that include content obtained via user input at a client device. An intent determination model is applied to the content to identify the user's intent. The virtual digital assistant identifies agents that are capable of servicing the intent are identified and retrieves contextual data relating to the message from a data store. An intent arbitration model is used to select one of the agents which is activated to provide assistance with the task. The contextual information may include global metrics of agent performance and/or information regarding the user's preferences.

Abstract: A computer system for language modeling may collect training data from one or more information sources, generate a spoken corpus containing text of transcribed speech, and generate a typed corpus containing typed text. The computer system may derive feature vectors from the spoken corpus, analyze the typed corpus to determine feature vectors representing items of typed text, and generate an unspeakable corpus by filtering the typed corpus to remove each item of typed text represented by a feature vector that is within a similarity threshold of a feature vector derived from the spoken corpus. The computer system may derive feature vectors from the unspeakable corpus and train a classifier to perform discriminative data selection for language modeling based on the feature vectors derived from the spoken corpus and the feature vectors derived from the unspeakable corpus.

Abstract: Methods and systems are provided for providing alternative query suggestions. For example, a spoken natural language expression may be received and converted to a textual query by a speech recognition component. The spoken natural language expression may include one or more words, terms, and/or phrases. A phonetically confusable segment of the textual query may be identified by a classifier component. The classifier component may determine at least one alternative query based on identifying at least the phonetically confusable segment of the textual query. The classifier may further determine whether to suggest the at least one alternative query based on whether the at least one alternative query is sensical and/or useful. When it is determined to suggest the at least one alternative query, the at least one alternative query may be provided to and displayed on a user interface display.

Abstract: Systems and methods are provided for improving language models for speech recognition by personalizing knowledge sources utilized by the language models to specific users or user-population characteristics. A knowledge source, such as a knowledge graph, is personalized for a particular user by mapping entities or user actions from usage history for the user, such as query logs, to the knowledge source. The personalized knowledge source may be used to build a personal language model by training a language model with queries corresponding to entities or entity pairs that appear in usage history. In some embodiments, a personalized knowledge source for a specific user can be extended based on personalized knowledge sources of similar users.

Abstract: An incremental speech recognition system. The incremental speech recognition system incrementally decodes a spoken utterance using an additional utterance decoder only when the additional utterance decoder is likely to add significant benefit to the combined result. The available utterance decoders are ordered in a series based on accuracy, performance, diversity, and other factors. A recognition management engine coordinates decoding of the spoken utterance by the series of utterance decoders, combines the decoded utterances, and determines whether additional processing is likely to significantly improve the recognition result. If so, the recognition management engine engages the next utterance decoder and the cycle continues. If the accuracy cannot be significantly improved, the result is accepted and decoding stops.

Abstract: A computer system for language modeling may collect training data from one or more information sources, generate a spoken corpus containing text of transcribed speech, and generate a typed corpus containing typed text. The computer system may derive feature vectors from the spoken corpus, analyze the typed corpus to determine feature vectors representing items of typed text, and generate an unspeakable corpus by filtering the typed corpus to remove each item of typed text represented by a feature vector that is within a similarity threshold of a feature vector derived from the spoken corpus. The computer system may derive feature vectors from the unspeakable corpus and train a classifier to perform discriminative data selection for language modeling based on the feature vectors derived from the spoken corpus and the feature vectors derived from the unspeakable corpus.

Abstract: A computer system for language modeling may collect training data from one or more information sources, generate a spoken corpus containing text of transcribed speech, and generate a typed corpus containing typed text. The computer system may derive feature vectors from the spoken corpus, analyze the typed corpus to determine feature vectors representing items of typed text, and generate an unspeakable corpus by filtering the typed corpus to remove each item of typed text represented by a feature vector that is within a similarity threshold of a feature vector derived from the spoken corpus. The computer system may derive feature vectors from the unspeakable corpus and train a classifier to perform discriminative data selection for language modeling based on the feature vectors derived from the spoken corpus and the feature vectors derived from the unspeakable corpus.

Abstract: Systems and methods are provided for training language models using in-domain-like data collected automatically from one or more data sources. The data sources (such as text data or user-interactional data) are mined for specific types of data, including data related to style, content, and probability of relevance, which are then used for language model training. In one embodiment, a language model is trained from features extracted from a knowledge graph modified into a probabilistic graph, where entity popularities are represented and the popularity information is obtained from data sources related to the knowledge. Embodiments of language models trained from this data are particularly suitable for domain-specific conversational understanding tasks where natural language is used, such as user interaction with a game console or a personal assistant application on personal device.

Abstract: The customization of language modeling components for speech recognition is provided. A list of language modeling components may be made available by a computing device. A hint may then be sent to a recognition service provider for combining the multiple language modeling components from the list. The hint may be based on a number of different domains. A customized combination of the language modeling components based on the hint may then be received from the recognition service provider.

Abstract: An incremental speech recognition system. The incremental speech recognition system incrementally decodes a spoken utterance using an additional utterance decoder only when the additional utterance decoder is likely to add significant benefit to the combined result. The available utterance decoders are ordered in a series based on accuracy, performance, diversity, and other factors. A recognition management engine coordinates decoding of the spoken utterance by the series of utterance decoders, combines the decoded utterances, and determines whether additional processing is likely to significantly improve the recognition result. If so, the recognition management engine engages the next utterance decoder and the cycle continues. If the accuracy cannot be significantly improved, the result is accepted and decoding stops.

Abstract: An incremental speech recognition system. The incremental speech recognition system incrementally decodes a spoken utterance using an additional utterance decoder only when the additional utterance decoder is likely to add significant benefit to the combined result. The available utterance decoders are ordered in a series based on accuracy, performance, diversity, and other factors. A recognition management engine coordinates decoding of the spoken utterance by the series of utterance decoders, combines the decoded utterances, and determines whether additional processing is likely to significantly improve the recognition result. If so, the recognition management engine engages the next utterance decoder and the cycle continues. If the accuracy cannot be significantly improved, the result is accepted and decoding stops.

Abstract: The customization of language modeling components for speech recognition is provided. A list of language modeling components may be made available by a computing device. A hint may then be sent to a recognition service provider for combining the multiple language modeling components from the list. The hint may be based on a number of different domains. A customized combination of the language modeling components based on the hint may then be received from the recognition service provider.

Abstract: A computer system for language modeling may collect training data from one or more information sources, generate a spoken corpus containing text of transcribed speech, and generate a typed corpus containing typed text. The computer system may derive feature vectors from the spoken corpus, analyze the typed corpus to determine feature vectors representing items of typed text, and generate an unspeakable corpus by filtering the typed corpus to remove each item of typed text represented by a feature vector that is within a similarity threshold of a feature vector derived from the spoken corpus. The computer system may derive feature vectors from the unspeakable corpus and train a classifier to perform discriminative data selection for language modeling based on the feature vectors derived from the spoken corpus and the feature vectors derived from the unspeakable corpus.

Abstract: Methods and systems are provided for providing alternative query suggestions. For example, a spoken natural language expression may be received and converted to a textual query by a speech recognition component. The spoken natural language expression may include one or more words, terms, and/or phrases. A phonetically confusable segment of the textual query may be identified by a classifier component. The classifier component may determine at least one alternative query based on identifying at least the phonetically confusable segment of the textual query. The classifier may further determine whether to suggest the at least one alternative query based on whether the at least one alternative query is sensical and/or useful. When it is determined to suggest the at least one alternative query, the at least one alternative query may be provided to and displayed on a user interface display.