Abstract: The present disclosure includes systems and techniques relating to ranking search results of a search query. In general, the subject matter described in this specification can be embodied in a computer-implemented method that includes determining a measure of relevance for a document result within a context of a search query for which the document result is returned, the determining being based on a first number in relation to a second number, the first number corresponding to longer views of the document result, and the second number corresponding to at least shorter views of the document result; and outputting the measure of relevance to a ranking engine for ranking of search results, including the document result, for a new search corresponding to the search query. The subject matter described in this specification can also be embodied in various corresponding computer program products, apparatus and systems.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.

Abstract: A system ranks documents based, at least in part, on a ranking model. The ranking model may be generated to predict the likelihood that a document will be selected. The system may receive a search query and identify documents relating to the search query. The system may then rank the documents based, at least in part, on the ranking model and form search results for the search query from the ranked documents.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing an utterance, and the input acoustic sequence comprising a respective acoustic feature representation at each of a first number of time steps; processing the input acoustic sequence using a first neural network to convert the input acoustic sequence into an alternative representation for the input acoustic sequence; processing the alternative representation for the input acoustic sequence using an attention-based Recurrent Neural Network (RNN) to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings; and generating a sequence of substrings that represent a transcription of the utterance.

Abstract: The present disclosure includes systems and techniques relating to ranking search results of a search query. In general, the subject matter described in this specification can be embodied in a computer-implemented method that includes determining a measure of relevance for a document result within a context of a search query for which the document result is returned, the determining being based on a first number in relation to a second number, the first number corresponding to longer views of the document result, and the second number corresponding to at least shorter views of the document result; and outputting the measure of relevance to a ranking engine for ranking of search results, including the document result, for a new search corresponding to the search query. The subject matter described in this specification can also be embodied in various corresponding computer program products, apparatus and systems.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing an utterance, and the input acoustic sequence comprising a respective acoustic feature representation at each of a first number of time steps; processing the input acoustic sequence using a first neural network to convert the input acoustic sequence into an alternative representation for the input acoustic sequence; processing the alternative representation for the input acoustic sequence using an attention-based Recurrent Neural Network (RNN) to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings; and generating a sequence of substrings that represent a transcription of the utterance.

Abstract: Keyword suggestions that are category-aware (and field-proven) may be used to help advertisers better target the serving of their ads, and may reduce unused ad spot inventory. The advertiser can enter ad information, such as a creative, a landing Webpage, other keywords, etc. for example. A keyword facility may use this entered ad information as seed information to infer one or more categories. It may then request that the advertiser confirm or deny some basic feedback information (e.g., categories, Webpage information, etc.). For example, an advertiser may be provided with candidate categories and may be asked to confirm (e.g., using checkboxes) which of the categories are relevant to their ad. Keywords may be determined using at least the categories. The determined keywords may be provided to the advertiser as suggested keywords, or may automatically populate ad serving constraint information as targeting keywords.

Abstract: Methods, and systems, including computer programs encoded on computer storage media for generating compressed representations from a co-occurrence matrix. A method includes obtaining a set of sub matrices of a co-occurrence matrix, where each row of the co-occurrence matrix corresponds to a feature from a first feature vocabulary and each column of the co-occurrence matrix corresponds to a feature from a second feature vocabulary; selecting a sub matrix, wherein the sub matrix is associated with a particular row block and column block of the co-occurrence matrix; assigning respective d-dimensional initial row and column embedding vectors to each row and column from the particular row and column blocks, respectively; and determining a final row embedding vector and a final column embedding vector by iteratively adjusting the initial row embedding vectors and the initial column embedding vectors using the co-occurrence matrix.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reranking query completions based on activity session data. One of the methods includes receiving a query prefix from a user. Query completions are obtained for the query prefix. One or more likely queries that are likely to co-occur with a reference query in user activity sessions are obtained. If one of the likely queries matches one of the query completions, a modified ranking of the query completions is determined, including boosting a ranking of matching query completions. The modified ranking of the query completions is provided in response to receiving the query prefix.

Abstract: The present disclosure includes systems and techniques relating to ranking search results of a search query. In general, the subject matter described in this specification can be embodied in a computer-implemented method that includes determining a measure of relevance for a document result within a context of a search query for which the document result is returned, the determining being based on a first number in relation to a second number, the first number corresponding to longer views of the document result, and the second number corresponding to at least shorter views of the document result; and outputting the measure of relevance to a ranking engine for ranking of search results, including the document result, for a new search corresponding to the search query. The subject matter described in this specification can also be embodied in various corresponding computer program products, apparatus and systems.

Abstract: A method and an apparatus to provide a personalized page to a user have been disclosed. In one embodiment, a user is identified as a member of a first group and a member of a second group. The first group's level of interest (LOI) in a first item is identified, as well as the second group's LOI in a second item. The user's LOI in at least one of the first and the second items is identified.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reranking query completions based on activity session data. One of the methods includes receiving a query prefix from a user. Query completions are obtained for the query prefix. One or more likely queries that are likely to co-occur with a reference query in user activity sessions are obtained. If one of the likely queries matches one of the query completions, a modified ranking of the query completions is determined, including boosting a ranking of matching query completions. The modified ranking of the query completions is provided in response to receiving the query prefix.

Abstract: A method and an apparatus to provide a personalized page to a user have been disclosed. In one embodiment, a user is identified as a member of a first group and a member of a second group. The first group's level of interest (LOI) in a first item is identified, as well as the second group's LOI in a second item. The user's LOI in at least one of the first and the second items is identified.

Abstract: One embodiment of the present invention provides a system characterizes a document with respect to clusters of conceptually related words. Upon receiving a document containing a set of words, the system selects “candidate clusters” of conceptually related words that are related to the set of words. These candidate clusters are selected using a model that explains how sets of words are generated from clusters of conceptually related words. Next, the system constructs a set of components to characterize the document, wherein the set of components includes components for candidate clusters. Each component in the set of components indicates a degree to which a corresponding candidate cluster is related to the set of words.

Abstract: Systems and techniques relating to ranking search results of a search query include, in general, subject matter that can be embodied in a computer-implemented method that includes determining a measure of relevance for a document result within a context of a search query for which the document result is returned, the determining being based on a first number in relation to a second number, the first number corresponding to longer views of the document result, and the second number corresponding to at least shorter views of the document result; and outputting the measure of relevance to a ranking engine for ranking of search results, including the document result, for a new search corresponding to the search query. The subject matter described in this specification can also be embodied in various corresponding computer program products, apparatus and systems.

Abstract: One embodiment of the present invention provides a system that learns a generative model for textual documents. During operation, the system receives a current model, which contains terminal nodes representing random variables for words and cluster nodes representing clusters of conceptually related words. Within the current model, nodes are coupled together by weighted links, so that if a cluster node in the probabilistic model fires, a weighted link from the cluster node to another node causes the other node to fire with a probability proportionate to the link weight. The system also receives a set of training documents, wherein each training document contains a set of words. Next, the system applies the set of training documents to the current model to produce a new model.

Abstract: One embodiment of the present invention provides a system that learns a generative model for textual documents. During operation, the system receives a current model, which contains terminal nodes representing random variables for words and cluster nodes representing clusters of conceptually related words. Within the current model, nodes are coupled together by weighted links, so that if a cluster node in the probabilistic model fires, a weighted link from the cluster node to another node causes the other node to fire with a probability proportionate to the link weight. The system also receives a set of training documents, wherein each training document contains a set of words. Next, the system applies the set of training documents to the current model to produce a new model.

Abstract: Among other disclosed subject matter, a computer-implemented method includes identifying a first object that belongs to a first domain. The method includes identifying, using the first object, at least a first cluster node in a generative model that includes a plurality of first cluster nodes having weighted relationships to respective ones of a plurality of second objects. The method includes identifying, in response to identifying the first object, at least one of the second objects, the second object belonging to the first domain and being identified using the first cluster node and its respective weighted relationship.

Abstract: One embodiment of the present invention provides a system characterizes a document with respect to clusters of conceptually related words. Upon receiving a document containing a set of words, the system selects “candidate clusters” of conceptually related words that are related to the set of words. These candidate clusters are selected using a model that explains how sets of words are generated from clusters of conceptually related words. Next, the system constructs a set of components to characterize the document, wherein the set of components includes components for candidate clusters. Each component in the set of components indicates a degree to which a corresponding candidate cluster is related to the set of words.

Abstract: One embodiment of the present invention provides a system that learns a generative model for textual documents. During operation, the system receives a current model, which contains terminal nodes representing random variables for words and cluster nodes representing clusters of conceptually related words. Within the current model, nodes are coupled together by weighted links, so that if a cluster node in the probabilistic model fires, a weighted link from the cluster node to another node causes the other node to fire with a probability proportionate to the link weight. The system also receives a set of training documents, wherein each training document contains a set of words. Next, the system applies the set of training documents to the current model to produce a new model.