Abstract: There is provided a search system comprising a statistical model trained on text associated with a piece of content. The text associated with the piece of content is drawn from a plurality of different data sources. The system is configured to receive text input and generate using the statistical model an estimate of the likelihood that the piece of content is relevant given the text input. A corresponding method is also provided.

Abstract: There is provided a search system comprising a statistical model trained on text associated with a piece of content. The text associated with the piece of content is drawn from a plurality of different data sources. The system is configured to receive text input and generate using the statistical model an estimate of the likelihood that the piece of content is relevant given the text input. A corresponding method is also provided.

Abstract: The present invention provides systems and methods for integrating text prediction from a text prediction engine into a mechanism for searching/filtering/ordering a plurality of items. In one embodiment, the system comprises a text prediction engine configured to receive user text input relating to a sequence of two or more terms, generate a plurality of word predictions for a first term of the sequence of two or more terms and generate at least one word prediction for a second term of the sequence of two or more terms. The text prediction engine is configured to generate a distribution of candidate word predictions for the sequence of two or more terms using the plurality of word predictions for the first term and the at least one word prediction for the second term. The system further comprises a mechanism for filtering/searching/ordering a plurality of items.

Abstract: System and techniques for receiving text input into electronic devices and predicting a relevant image or label. In a first aspect, the system and techniques comprise receiving text input by a user and a prediction function trained on sections of text associated with an image or label. The prediction function is configured to receive the text input by the user, determine the relevance of the text input by the user to the sections of text associated with the image or label, and predict, based on the sections of text associated with the image or label the relevance of the image or label to the text input by the user. The systems and techniques reduce the burden of entering an image or label.

Abstract: A system comprising a feature identification means configured to generate one or more features from a plurality of samples, wherein each of the plurality of samples are sampled at a different time and correspond to a location of a single continuous gesture on a gesture-sensitive keyboard as the gesture is being performed and, wherein each of the one or more features relates to one of a plurality of targets of the gesture sensitive keyboard that a user may have intended to input when performing the gesture. The system comprises a prediction means configured to predict one or more terms from the one or more features, the prediction means comprising a prefix tree generating means configured to generate a prefix tree of terms which includes the one or more features, a path finding means configured to find one or more paths through the prefix tree of terms given the one or more features, and a predictor. A corresponding method is also provided.

Abstract: The present invention provides systems and methods for integrating text prediction from a text prediction engine into a mechanism for searching/filtering/ordering a plurality of items. In one embodiment, the system comprises a text prediction engine configured to receive user text input relating to a sequence of two or more terms, generate a plurality of word predictions for a first term of the sequence of two or more terms and generate at least one word prediction for a second term of the sequence of two or more terms. The text prediction engine is configured to generate a distribution of candidate word predictions for the sequence of two or more terms using the plurality of word predictions for the first term and the at least one word prediction for the second term. The system further comprises a mechanism for filtering/searching/ordering a plurality of items.

Abstract: A system comprising a feature identification means configured to generate one or more features from a plurality of samples, wherein each of the plurality of samples are sampled at a different time and correspond to a location of a single continuous gesture on a gesture-sensitive keyboard as the gesture is being performed and, wherein each of the one or more features relates to one of a plurality of targets of the gesture sensitive keyboard that a user may have intended to input when performing the gesture. The system comprises a prediction means configured to predict one or more terms from the one or more features, the prediction means comprising a prefix tree generating means configured to generate a prefix tree of terms which includes the one or more features, a path finding means configured to find one or more paths through the prefix tree of terms given the one or more features, and a predictor. A corresponding method is also provided.

Abstract: A system and method for inputting text A system (10) comprising a feature identification means (2) configured to generate one or more features (12) from a plurality of samples (11), wherein each of the plurality of samples (11) are sampled at a different time and correspond to a location of a single continuous gesture on a gesture-sensitive keyboard as the gesture is being performed and, wherein each of the one or more features (12) relates to one of a plurality of targets of the gesture sensitive keyboard that a user may have intended to input when performing the gesture.

Abstract: There are provided systems and methods for predicting an image/label relevant to text input by a user. In a first aspect, there is provided a system comprising a means for receiving text input by a user and a prediction means trained on sections of text associated with an image/label. The prediction means is configured to receive the text input by the user, determine the relevance of the text input by the user to the sections of text associated with the image/label, and predict on image/label the basis of the sections of text associated with the language model 10 image/label the relevance of the image/label to the text input by the user. The systems and methods of the present invention reduce the burden of entering an image/label.

Abstract: There is provided a search system comprising a statistical model trained on text associated with a piece of content. The text associated with the piece of content is drawn from a plurality of different data sources. The system is configured to receive text input and generate using the statistical model an estimate of the likelihood that the piece of content is relevant given the text input. A corresponding method is also provided.

Abstract: A system and method for inputting text A system (10) comprising a feature identification means (2) configured to generate one or more features (12) from a plurality of samples (11), wherein each of the plurality of samples (11) are sampled at a different time and correspond to a location of a single continuous gesture on a gesture-sensitive keyboard as the gesture is being performed and, wherein each of the one or more features (12) relates to one of a plurality of targets of the gesture sensitive keyboard that a user may have intended to input when performing the gesture.

Abstract: A method and apparatus for use in servicing a search request where the search request comprises a plurality of parts (such as characters) and establishing a list of tokens where the tokens correspond to elements of objects and have a numerical value. For each part of the search request a subset of the list is determined, said subset identifying a set of objects which may satisfy the search query. The subsets may be identified iteratively. Token encoding is used to encode tokens based on a content of said elements and, in this case, the same token encoding is used to encode the parts of the search request. The token encoding may comprise differential encoding. In certain embodiments, resource requirements necessary to complete the search request are determined based on the identified subsets.

Abstract: A method and apparatus for use in servicing a search request where the search request comprises a plurality of parts (such as characters) and establishing a list of tokens where the tokens correspond to elements of objects and have a numerical value. For each part of the search request a subset of the list is determined, said subset identifying a set of objects which may satisfy the search query. The subsets may be identified iteratively. Token encoding is used to encode tokens based on a content of said elements and, in this case, the same token encoding is used to encode the parts of the search request. The token encoding may comprise differential encoding. In certain embodiments, resource requirements necessary to complete the search request are determined based on the identified subsets.