Abstract: Techniques in optimized placement for efficiency for accelerated deep learning provide improvements in one or more of accuracy, performance, and energy efficiency. An array of processing elements comprising a portion of a neural network accelerator performs flow-based computations on wavelets of data. Each processing element comprises a compute element to execute programmed instructions using the data and a router to route the wavelets. The routing is in accordance with virtual channel specifiers of the wavelets and controlled by routing configuration information of the router. A software stack determines optimized placement based on a description of a neural network. The determined placement is used to configure the routers including usage of the respective colors. The determined placement is used to configure the compute elements including the respective programmed instructions each is configured to execute.

Abstract: Techniques in placement of compute and memory for accelerated deep learning provide improvements in one or more of accuracy, performance, and energy efficiency. An array of processing elements comprising a portion of a neural network accelerator performs flow-based computations on wavelets of data. Each processing element comprises a compute element to execute programmed instructions using the data and a router to route the wavelets. The routing is in accordance with virtual channel specifiers of the wavelets and controlled by routing configuration information of the router. A software stack determines placement of compute resources and memory resources based on a description of a neural network. The determined placement is used to configure the routers including usage of the respective colors. The determined placement is used to configure the compute elements including the respective programmed instructions each is configured to execute.

Abstract: Techniques in distributed placement of linear operators for accelerated deep learning provide improvements in one or more of accuracy, performance, and energy efficiency. An array of processing elements comprising a portion of a neural network accelerator performs flow-based computations on wavelets of data. Each processing element comprises a compute element to execute programmed instructions using the data and a router to route the wavelets. The routing is in accordance with virtual channel specifiers of the wavelets and controlled by routing configuration information of the router. A software stack determines distributed placement of linear operators based on a description of a neural network. The determined placement is used to configure the routers including usage of the respective colors. The determined placement is used to configure the compute elements including the respective programmed instructions each is configured to execute.

Abstract: Embodiments are disclosed for transliterating text entries across different script systems. A method according to some embodiments includes steps of: receiving an input string in a first script system input using a keyboard; segmenting, using a probabilistic model, the input string into phonemes that correspond to characters or sets of characters in a second script system; converting the phonemes in the first script system into the characters or sets of characters in the second script system, the characters or sets of characters forming a word or a word prefix in the second script system; and outputting the word or the word prefix in the second script system.

Abstract: Embodiments are disclosed for transliterating text entries across different script systems. A method according to some embodiments includes steps of: receiving an input string in a first script system input using a keyboard; segmenting, using a probabilistic model, the input string into phonemes that correspond to characters or sets of characters in a second script system; converting the phonemes in the first script system into the characters or sets of characters in the second script system, the characters or sets of characters forming a word or a word prefix in the second script system; and outputting the word or the word prefix in the second script system.

Abstract: Embodiments are disclosed for transliterating text entries across different script systems. A method according to some embodiments includes steps of: receiving an input string in a first script system input using a keyboard; segmenting, using a probabilistic model, the input string into phonemes that correspond to characters or sets of characters in a second script system; converting the phonemes in the first script system into the characters or sets of characters in the second script system, the characters or sets of characters forming a word or a word prefix in the second script system; and outputting the word or the word prefix in the second script system.

Abstract: Embodiments are disclosed for transliteration decoding using a tree structure. A method according to some embodiments includes steps of: generating a tree structure for an input string in a first script system, the tree structure including nodes representing segments of the input string; identifying segmentation candidates for the input string based on paths of the tree structure, the segmentation candidates segmenting the input string into character groups; selecting a segmentation candidate based on probabilities of the segmentation candidates predicted by a probabilistic model; segmenting the input string into character groups that correspond to characters in a second script system; decoding the character groups in the first script system into the characters in the second script system, the characters forming a word or a word prefix in the second script system; and outputting the word or the word prefix in the second script system.

Abstract: The invention provides a display interface in a social networking system that enables the presentation of information related to a user in a timeline or map view. The system accesses information about a user of a social networking system, including both data about the user and social network activities related to the user. The system then selects one or more of these pieces of data and/or activities from a certain time period and gathers them into timeline units based on their relatedness and their relevance to users. These timeline units are ranked by relevance to the user, and are used to generate a timeline or map view for the user containing visual representations of the timeline units organized by location or time. The timeline or map view is then provided to other users of the social networking system that wish to view information about the user.

Abstract: A system for identifying language(s) for content items is disclosed. The system can identify different languages for content item words segments by identifying segment languages that maximize a probability across the segments. The probability can be a combination of: an author's likelihood for the language identified for the first word; a combination of transition frequencies for selected languages identified for words, the transition frequencies indicating likelihoods that a transition occurred to the selected language from the previous word's language; and a combination of observation probabilities indicating, for a given word in the content item, a likelihood the given word is in the identified language. For an in-vocabulary word, the observation probabilities can be based on learned probability for that word. For an out-of-vocabulary word, the probability can be computed by breaking the word into overlapping n-grams and computing combined learned probabilities that each n-gram is in the given language.

Abstract: A system for identifying language(s) for content items is disclosed. The system can identify different languages for content item words segments by identifying segment languages that maximize a probability across the segments. The probability can be a combination of: an author's likelihood for the language identified for the first word; a combination of transition frequencies for selected languages identified for words, the transition frequencies indicating likelihoods that a transition occurred to the selected language from the previous word's language; and a combination of observation probabilities indicating, for a given word in the content item, a likelihood the given word is in the identified language. For an in-vocabulary word, the observation probabilities can be based on learned probability for that word. For an out-of-vocabulary word, the probability can be computed by breaking the word into overlapping n-grams and computing combined learned probabilities that each n-gram is in the given language.

Abstract: Embodiments are disclosed for transliterating text entries across different script systems. A method according to some embodiments includes steps of: receiving an input string in a first script system input using a keyboard; segmenting, using a probabilistic model, the input string into phonemes that correspond to characters or sets of characters in a second script system; converting the phonemes in the first script system into the characters or sets of characters in the second script system, the characters or sets of characters forming a word or a word prefix in the second script system; and outputting the word or the word prefix in the second script system.

Abstract: Embodiments are disclosed for transliteration decoding using a tree structure. A method according to some embodiments includes steps of: generating a tree structure for an input string in a first script system, the tree structure including nodes representing segments of the input string; identifying segmentation candidates for the input string based on paths of the tree structure, the segmentation candidates segmenting the input string into character groups; selecting a segmentation candidate based on probabilities of the segmentation candidates predicted by a probabilistic model; segmenting the input string into character groups that correspond to characters in a second script system; decoding the character groups in the first script system into the characters in the second script system, the characters forming a word or a word prefix in the second script system; and outputting the word or the word prefix in the second script system.

Abstract: At least one embodiment of this disclosure includes a method of inferring attribute labels for a user in a social networking system based on the user's social connections and user-specified attribute labels in the social networking system. The method can include: establishing variational equations based on attribute labels of nodes in an ego network in a social graph of a social networking system; determining likelihood scores for at least a portion of the attribute labels of neighboring nodes from a focal user node in the ego network based on user-specified attribute labels from the social networking system; and calculating probability distributions of possible attribute labels for the focal user node of the ego network based on the variational equations and the likelihood scores.

Abstract: At least one embodiment of this disclosure includes a method of inferring attribute labels for a user in a social networking system based on the user's social connections and user-specified attribute labels in the social networking system. The method can include: establishing variational equations based on attribute labels of nodes in an ego network in a social graph of a social networking system; determining likelihood scores for at least a portion of the attribute labels of neighboring nodes from a focal user node in the ego network based on user-specified attribute labels from the social networking system; and calculating probability distributions of possible attribute labels for the focal user node of the ego network based on the variational equations and the likelihood scores.

Abstract: At least one embodiment of this disclosure includes a method of inferring attribute labels for a user in a social networking system based on the user's social connections and user-specified attribute labels in the social networking system. The method can include: establishing variational equations based on attribute labels of nodes in an ego network in a social graph of a social networking system; determining likelihood scores for at least a portion of the attribute labels of neighboring nodes from a focal user node in the ego network based on user-specified attribute labels from the social networking system; and calculating probability distributions of possible attribute labels for the focal user node of the ego network based on the variational equations and the likelihood scores.

Abstract: The invention provides a display interface in a social networking system that enables the presentation of information related to a user in a timeline or map view. The system accesses information about a user of a social networking system, including both data about the user and social network activities related to the user. The system then selects one or more of these pieces of data and/or activities from a certain time period and gathers them into timeline units based on their relatedness and their relevance to users. These timeline units are ranked by relevance to the user, and are used to generate a timeline or map view for the user containing visual representations of the timeline units organized by location or time. The timeline or map view is then provided to other users of the social networking system that wish to view information about the user.

Abstract: The invention provides a display interface in a social networking system that enables the presentation of information related to a user in a timeline or map view. The system accesses information about a user of a social networking system, including both data about the user and social network activities related to the user. The system then selects one or more of these pieces of data and/or activities from a certain time period and gathers them into timeline units based on their relatedness and their relevance to users. These timeline units are ranked by relevance to the user, and are used to generate a timeline or map view for the user containing visual representations of the timeline units organized by location or time. The timeline or map view is then provided to other users of the social networking system that wish to view information about the user.

Abstract: The invention provides a display interface in a social networking system that enables the presentation of information related to a user in a timeline or map view. The system accesses information about a user of a social networking system, including both data about the user and social network activities related to the user. The system then selects one or more of these pieces of data and/or activities from a certain time period and gathers them into timeline units based on their relatedness and their relevance to users. These timeline units are ranked by relevance to the user, and are used to generate a timeline or map view for the user containing visual representations of the timeline units organized by location or time. The timeline or map view is then provided to other users of the social networking system that wish to view information about the user.