Abstract: A computer-implemented method can include receiving, at a computing device having one or more processors, a user input in a first writing system. The method can include determining one or more candidates based on the user input that correspond to the user input represented in a second writing system different than the first writing system. The method can include determining whether at least one of the candidates corresponds to a proper name of a geographic location and, when at least one of the candidates corresponds to the proper name of the geographic location, determining a local name of the geographic location. The local name can be the proper name of the geographic location in a local language associated with the geographic location. The method can include augmenting the one or more candidates to include the local name to obtain an augmented candidate list, and outputting the augmented candidate list.

Abstract: A computer-implemented method can include receiving, at a computing device having one or more processors, a user input in a first writing system. The method can include determining one or more candidates based on the user input that correspond to the user input represented in a second writing system different than the first writing system. The method can include determining whether at least one of the candidates corresponds to a proper name of a geographic location and, when at least one of the candidates corresponds to the proper name of the geographic location, determining a local name of the geographic location. The local name can be the proper name of the geographic location in a local language associated with the geographic location. The method can include augmenting the one or more candidates to include the local name to obtain an augmented candidate list, and outputting the augmented candidate list.

Abstract: Methods, systems, apparatus, including computer program products for browsing and editing input for an input method editor. In one implementation, a method is provided. The method includes receiving an input sequence of characters in a first writing system; identifying in the input sequence of characters one or more first subsequences of consecutive characters, where each subsequence represents a syllable in a different, second writing system; identifying in the input sequence of characters one or more second subsequences, where each second subsequence includes one or more consecutive first subsequences and represents a term in the different, second writing system; determining one or more boundaries that delimit the one or more second subsequences; and generating one or more selectable indicators for display in a user interface, where each of the one or more selectable indicators identifies a respective second subsequence delimited by the one or more boundaries.

Abstract: A computer-implemented technique includes receiving a first input from a user at a user device, the first input including a first word of a first alphabet-based language, which is a transliteration of a non-alphabet-based language, which is one of a logogram-based language and a syllabogram-based language. The technique then compares the first words to pluralities of potential translated words from one or more datastores associated with a second alphabet-based language and the logogram-based or syllabogram-based languages. The technique may then generate a probability score for each of the pluralities of potential translated words, the probability score indicating a likelihood of an appropriate translation. The techniques may then provide the user with some or all of the pluralities of potential translated words and the user may select an appropriate translated word to obtain a selected word, which may then be displayed via a display of the user device.

Abstract: A computer-implemented method can include receiving an input from a user. The input can include one or more characters in a first script representative of text in a particular language. The input can be received in association with a document. The method can include determining a context of the input based on one or more semantic topics of the document associated with the input. One or more candidates for the input can be determined based on (i) the input, (ii) the context of the input, and (iii) a language model. The candidates can include one or more characters in a second script representative of the text in the particular language. The language model can express a probability of occurrence of the one or more candidates in the particular language. The method can further include outputting a list of the one or more candidates for display to the user.

Abstract: Described is a technology by which co-located query patterns are mined from a data space such as a geographic search log. An overall data space (basic) approach and/or a lattice-based approach may be used when mining. The data space contains objects, each comprising associated type and location information. The location information is used to determine the distance between different two or more types of objects, e.g., pairs. The frequency of occurrence of those pairs within the data space determines whether that pairing of object types indicates a co-located pattern. Also described is partitioning the data space into regions, including for the purpose of categorizing a co-located pattern as a local pattern or a global pattern based on how that co-located pattern is distributed among the regions.

Abstract: A method and system for facilitating text input is disclosed. The method comprises: invoking an input assistant from within an application in an operating environment at a client, the input assistant being a standalone input service within the same operating environment as the application, receiving a text string from a user in an input field of the application, providing, by the input assistant, input prediction for completing the text string, selecting an input text of at least one word in the input field of the application, retrieving, by the input assistant, text content related to the input text from one or more text assistance services in communication with the input assistant, presenting the received text content to the user for assistance in the user's text input.

Abstract: A computer-implemented technique includes receiving a first input from a user at a user device, the first input including a first word of a first alphabet-based language, which is a transliteration of a non-alphabet-based language, which is one of a logogram-based language and a syllabogram-based language. The technique then compares the first words to pluralities of potential translated words from one or more datastores associated with a second alphabet-based language and the logogram-based or syllabogram-based languages. The technique may then generate a probability score for each of the pluralities of potential translated words, the probability score indicating a likelihood of an appropriate translation. The techniques may then provide the user with some or all of the pluralities of potential translated words and the user may select an appropriate translated word to obtain a selected word, which may then be displayed via a display of the user device.

Abstract: A computer-implemented technique includes receiving a first input from a user at a user device, the first input including a first word of a first alphabet-based language, which is a transliteration of a non-alphabet-based language, which is one of a logogram-based language and a syllabogram-based language. The technique then compares the first words to pluralities of potential translated words from one or more datastores associated with a second alphabet-based language and the logogram-based or syllabogram-based languages. The technique may then generate a probability score for each of the pluralities of potential translated words, the probability score indicating a likelihood of an appropriate translation. The techniques may then provide the user with some or all of the pluralities of potential translated words and the user may select an appropriate translated word to obtain a selected word, which may then be displayed via a display of the user device.

Abstract: A computer-implemented method for assisting a user to input Vietnamese text to a user device lacking a subset of characters in a Vietnamese alphabet includes receiving a character input by a user, determining three words previously input by the user, the three words having already had diacritical marks inserted, transmitting the three words and the character to a server via a network, receiving first and second information corresponding to the character from the server via the network, the first and second information generated at the server based on a context of the three words, the context determined at the server using a language model, the first and second information indicating whether the character requires a diacritical mark and a specific diacritical mark, respectively, generating a modified character comprising a character in the Vietnamese alphabet based on the character and the first and second information, and displaying the modified character.

Abstract: A computer-implemented technique includes receiving a first input from a user at a user device, the first input including a first word of a first alphabet-based language, which is a transliteration of a non-alphabet-based language, which is one of a logogram-based language and a syllabogram-based language. The technique then compares the first words to pluralities of potential translated words from one or more datastores associated with a second alphabet-based language and the logogram-based or syllabogram-based languages. The technique may then generate a probability score for each of the pluralities of potential translated words, the probability score indicating a likelihood of an appropriate translation. The techniques may then provide the user with some or all of the pluralities of potential translated words and the user may select an appropriate translated word to obtain a selected word, which may then be displayed via a display of the user device.

Abstract: A computer-implemented method for assisting a user to input Vietnamese text to a user device lacking a subset of characters in a Vietnamese alphabet includes receiving a character input by a user, determining three words previously input by the user, the three words having already had diacritical marks inserted, transmitting the three words and the character to a server via a network, receiving first and second information corresponding to the character from the server via the network, the first and second information generated at the server based on a context of the three words, the context determined at the server using a language model, the first and second information indicating whether the character requires a diacritical mark and a specific diacritical mark, respectively, generating a modified character comprising a character in the Vietnamese alphabet based on the character and the first and second information, and displaying the modified character.

Abstract: Methods, systems, apparatus, including computer program products for browsing and editing input for an input method editor. In one implementation, a method is provided. The method includes receiving an input sequence of characters in a first writing system; identifying in the input sequence of characters one or more first subsequences of consecutive characters, where each subsequence represents a syllable in a different, second writing system; identifying in the input sequence of characters one or more second subsequences, where each second subsequence includes one or more consecutive first subsequences and represents a term in the different, second writing system; determining one or more boundaries that delimit the one or more second subsequences; and generating one or more selectable indicators for display in a user interface, where each of the one or more selectable indicators identifies a respective second subsequence delimited by the one or more boundaries.

Abstract: Described is using density to efficiently mine co-location patterns, such as closely located businesses frequently found together in business listing databases, geographic search logs, and/or GPS-based data. A data space of such information is geographically partitioned into a grid of cells, with dense cells scanned first. A dynamic upper bound of prevalence measure of co-location patterns is maintained during the scanning process. If the current upper bound is smaller than a threshold, the scanning is stopped, thereby significantly reducing the computation cost for processing many cells, while providing suitable results.

Abstract: A method and system for facilitating text input is disclosed. The method comprises: invoking an input assistant from within an application in an operating environment at a client, the input assistant being a standalone input service within the same operating environment as the application, receiving a text string from a user in an input field of the application, providing, by the input assistant, input prediction for completing the text string, selecting an input text of at least one word in the input field of the application, retrieving, by the input assistant, text content related to the input text from one or more text assistance services in communication with the input assistant, presenting the received text content to the user for assistance in the user's text input.

Abstract: A classification system trains a classifier to classify blocks of the web page into various classifications of the function of the block. The classification system trains a classifier using training web pages. To train a classifier, the classification system identifies the blocks of the training web pages, generates feature vectors for the blocks that include a linguistic feature, and inputs classification labels for each block. The classification system learns the coefficients of the classifier using any of a variety of machine learning techniques. The classification system can then use the classifier to classify blocks of web pages.

Abstract: Described is using density to efficiently mine co-location patterns, such as closely located businesses frequently found together in business listing databases, geographic search logs, and/or GPS-based data. A data space of such information is geographically partitioned into a grid of cells, with dense cells scanned first. A dynamic upper bound of prevalence measure of co-location patterns is maintained during the scanning process. If the current upper bound is smaller than a threshold, the scanning is stopped, thereby significantly reducing the computation cost for processing many cells, while providing suitable results.

Abstract: Described is a technology by which co-located query patterns are mined from a data space such as a geographic search log. An overall data space (basic) approach and/or a lattice-based approach may be used when mining. The data space contains objects, each comprising associated type and location information. The location information is used to determine the distance between different two or more types of objects, e.g., pairs. The frequency of occurrence of those pairs within the data space determines whether that pairing of object types indicates a co-located pattern. Also described is partitioning the data space into regions, including for the purpose of categorizing a co-located pattern as a local pattern or a global pattern based on how that co-located pattern is distributed among the regions.

Abstract: A classification system trains a classifier to classify blocks of the web page into various classifications of the function of the block. The classification system trains a classifier using training web pages. To train a classifier, the classification system identifies the blocks of the training web pages, generates feature vectors for the blocks that include a linguistic feature, and inputs classification labels for each block. The classification system learns the coefficients of the classifier using any of a variety of machine learning techniques. The classification system can then use the classifier to classify blocks of web pages.