Abstract: Methods, systems, and computer-readable media related to a technique for providing handwriting input functionality on a user device. A handwriting recognition module is trained to have a repertoire comprising multiple non-overlapping scripts and capable of recognizing tens of thousands of characters using a single handwriting recognition model. The handwriting input module provides real-time, stroke-order and stroke-direction independent handwriting recognition for multi-character handwriting input. In particular, real-time, stroke-order and stroke-direction independent handwriting recognition is provided for multi-character, or sentence level Chinese handwriting recognition. User interfaces for providing the handwriting input functionality are also disclosed.

Abstract: Systems and processes for operating a digital assistant are provided. In accordance with one or more examples, a method includes, at a user device with one or more processors and memory, receiving unstructured natural language information from at least one user. The method also includes, in response to receiving the unstructured natural language information, determining whether event information is present in the unstructured natural language information. The method further includes, in accordance with a determination that event information is present within the unstructured natural language information, determining whether an agreement on an event is present in the unstructured natural language information. The method further includes, in accordance with a determination that an agreement on an event is present, determining an event type of the event and providing an event description based on the event type.

Abstract: The embodiments set forth techniques for sorting emails within an email application. The technique can include: (1) accessing a plurality of emails, where each email is included in a respective folder of one or more folders, (2) establishing a set of n-grams based on the plurality of emails, (3) for each n-gram in the set of n-grams: calculating a respective normalized entropy for the n-gram, and calculating a respective indexing power for the n-gram based on its respective normalized entropy, (4) ranking the n-grams based on their respective indexing powers to establish a ranked list of n-grams, and (5) establishing, for each folder of the one or more folders, a respective set of high-value n-grams based on the ranked list of n-grams. In turn, the high-value n-grams can be compared against n-grams of a new email to identify a target folder into which the new email should be sorted.

Abstract: Systems and processes for operating a digital assistant are provided. In accordance with one or more examples, a method includes, receiving training data for a data-driven learning network. The training data include a plurality of word sequences. The method further includes obtaining representations of an initial set of semantic categories associated with the words included in the training data; and training the data-driven learning network based on the plurality of word sequences included in the training data and based on the representations of the initial set of semantic categories. The training is performed using the word sequences in their entirety. The method further includes obtaining, based on the trained data-driven learning network, representations of a set of semantic embeddings of the words included in the training data; and providing the representations of the set of semantic embeddings to at least one of a plurality of different natural language processing tasks.

Abstract: Systems and processes for language identification using recurrent neural networks are provided. An example method includes, at an electronic device, receiving a first typed character of a character sequence and determining a character context of the first typed character based on the first typed character and a second typed character of the character sequence. The method further includes determining a confidence level that the character sequence is associated with a language of a plurality of languages based on the character context of the first typed character, and determining whether the confidence level exceeds a threshold, in accordance with a determination that the confidence level exceeds the threshold, providing the language as a candidate language, and in accordance with a determination that the confidence level does not exceed the threshold, forgoing providing the language as a candidate language.

Abstract: Methods, systems, and computer-readable media related to a technique for providing handwriting input functionality on a user device. A handwriting recognition module is trained to have a repertoire comprising multiple non-overlapping scripts and capable of recognizing tens of thousands of characters using a single handwriting recognition model. The handwriting input module provides real-time, stroke-order and stroke-direction independent handwriting recognition for multi-character handwriting input. In particular, real-time, stroke-order and stroke-direction independent handwriting recognition is provided for multi-character, or sentence level Chinese handwriting recognition. User interfaces for providing the handwriting input functionality are also disclosed.

Abstract: Systems and processes for operating an intelligent automated assistant to provide a set of predicted responses are provided. An example method includes, at an electronic device having one or more processors, receiving one or more messages and analyzing the unstructured natural language information of the one or more messages. The method also includes determining, based on the analysis of the unstructured natural language information, whether one or more predicted responses are to be provided. The method further includes, in accordance with a determination that one or more predicted responses are to be provided, determining, from a plurality of sets of candidate predicted responses, one set of predicted responses to be provided to the user based on context information. The method further includes providing the determined set of one or more predicted responses to the user.

Abstract: Systems and processes for efficient word encoding are provided. In accordance with one example, a method includes, at an electronic device with one or more processors and memory, receiving a user input including a word sequence, and providing a representation of a current word of the word sequence. The representation of the current word may be indicative of a class of a plurality of classes and a word associated with the class. The method further includes determining a current word context based on the representation of the current word and a previous word context, and providing a representation of a next word of the word sequence. The representation of the next word of the word sequence may be based on the current word context. The method further includes displaying, proximate to the user input, the next word of the word sequence.

Abstract: Methods, systems, and computer-readable media related to a technique for providing handwriting input functionality on a user device. A handwriting recognition module is trained to have a repertoire comprising multiple non-overlapping scripts and capable of recognizing tens of thousands of characters using a single handwriting recognition model. The handwriting input module provides real-time, stroke-order and stroke-direction independent handwriting recognition for multi-character handwriting input. In particular, real-time, stroke-order and stroke-direction independent handwriting recognition is provided for multi-character, or sentence level Chinese handwriting recognition. User interfaces for providing the handwriting input functionality are also disclosed.

Abstract: The present disclosure generally relates to systems and processes for emoji word sense disambiguation. In one example process, a word sequence is received. A word-level feature representation is determined for each word of the word sequence and a global semantic representation for the word sequence is determined. For a first word of the word sequence, an attention coefficient is determined based on a congruence between the word-level feature representation of the first word and the global semantic representation for the word sequence. The word-level feature representation of the first word is adjusted based on the attention coefficient. An emoji likelihood is determined based on the adjusted word-level feature representation of the first word. In accordance with the emoji likelihood satisfying one or more criteria, an emoji character corresponding to the first word is presented for display.

Abstract: Systems and methods for proactively identifying and surfacing relevant content are disclosed herein. An example method includes: detecting, via the touch-sensitive display, a search activation gesture from a user of the electronic device. The method also includes: in response to detecting only the search activation gesture, displaying a search interface on substantially all of the touch-sensitive display, the search interface including: (i) a search entry portion; and (ii) a predictions portion with one or more user interface objects each associated with a respective locally-installed application. Each respective locally-installed application is selected from among a plurality of locally-installed applications for inclusion in the predictions portion based on an application usage history associated with the user of the electronic device.

Abstract: Systems and methods for proactively identifying and surfacing relevant content on an electronic device with a touch-sensitive display are disclosed herein. In one aspect, a method includes executing, on the device, an application in response to an instruction from a user of the electronic device. While executing the application, the method further includes collecting usage data. The usage data at least includes one or more actions performed by the user within the application. The method also includes: automatically, without human intervention, obtaining at least one trigger condition based on the collected usage data and associating the at least one trigger condition with a particular action of the one or more actions performed by the user within the application. Upon determining that the at least one trigger condition has been satisfied, the method includes providing an indication to the user that the particular action associated with the trigger condition is available.

Abstract: The present disclosure generally relates to integrated text conversion and prediction. In an example process, a current character input of a first writing system is received. A first current character context in the first writing system is determined based on the current character input and a first previous character context in the first writing system. A second current character context in a second writing system is determined based on the first current character context, a second previous character context in the second writing system, and a character representation in the second writing system. A current word context in the second writing system is determined based on the second current character context, a previous word context in the second writing system, and a word representation in the second writing system. Based on the current word context, a probability distribution over a word inventory in the second writing system is determined.

Abstract: Exemplary embodiments of methods and apparatuses for automatic speech recognition are described. First model parameters associated with a first representation of an input signal are generated. The first representation of the input signal is a discrete parameter representation. Second model parameters associated with a second representation of the input signal are generated. The second representation of the input signal includes a continuous parameter representation of residuals of the input signal. The first representation of the input signal includes discrete parameters representing first portions of the input signal. The second representation includes discrete parameters representing second portions of the input signal that are smaller than the first portions. Third model parameters are generated to couple the first representation of the input signal with the second representation of the input signal. The first representation and the second representation of the input signal are mapped into a vector space.

Abstract: The embodiments set forth techniques for sorting emails within an email application. The technique can include: (1) accessing a plurality of emails, where each email is included in a respective folder of one or more folders, (2) establishing a set of n-grams based on the plurality of emails, (3) for each n-gram in the set of n-grams: calculating a respective normalized entropy for the n-gram, and calculating a respective indexing power for the n-gram based on its respective normalized entropy, (4) ranking the n-grams based on their respective indexing powers to establish a ranked list of n-grams, and (5) establishing, for each folder of the one or more folders, a respective set of high-value n-grams based on the ranked list of n-grams. In turn, the high-value n-grams can be compared against n-grams of a new email to identify a target folder into which the new email should be sorted.

Abstract: Systems and methods for proactively assisting users with accurately locating a parked vehicle are disclosed herein. An example method includes: automatically, and without instructions from a user: determining that a user of the electronic device is in a vehicle that has come to rest at a geographic location. Upon determining that the user has left the vehicle at the geographic location, the method includes automatically, and without instructions from a user: determining whether positioning information, retrieved from the location sensor to identify the geographic location, satisfies accuracy criteria. Upon determining that the positioning information does not satisfy the accuracy criteria, the method includes: providing a prompt to the user to input information about the geographic location. In response to providing the prompt, the method includes receiving information from the user about the geographic location and storing the information as vehicle location information.

Abstract: The present disclosure generally relates to systems and processes for morpheme-based word prediction. An example method includes receiving a current word; determining a context of the current word based on the current word and a context of a previous word; determining, using a morpheme-based language model, a likelihood of a prefix based on the context of the current word; determining, using the morpheme-based language model, a likelihood of a stem based on the context of the current word; determining, using the morpheme-based language model, a likelihood of a suffix based on the context of the current word; determining a next word based on the likelihood of the prefix, the likelihood of the stem, and the likelihood of the suffix; and providing an output including the next word.

Abstract: The present disclosure generally relates to systems and processes for emoji word sense disambiguation. In one example process, a word sequence is received. A word-level feature representation is determined for each word of the word sequence and a global semantic representation for the word sequence is determined. For a first word of the word sequence, an attention coefficient is determined based on a congruence between the word-level feature representation of the first word and the global semantic representation for the word sequence. The word-level feature representation of the first word is adjusted based on the attention coefficient. An emoji likelihood is determined based on the adjusted word-level feature representation of the first word. In accordance with the emoji likelihood satisfying one or more criteria, an emoji character corresponding to the first word is presented for display.

Abstract: Systems and processes for operating an intelligent automated assistant to provide a set of predicted responses are provided. An example method includes, at an electronic device having one or more processors, receiving one or more messages and analyzing the unstructured natural language information of the one or more messages. The method also includes determining, based on the analysis of the unstructured natural language information, whether one or more predicted responses are to be provided. The method further includes, in accordance with a determination that one or more predicted responses are to be provided, determining, from a plurality of sets of candidate predicted responses, one set of predicted responses to be provided to the user based on context information. The method further includes providing the determined set of one or more predicted responses to the user.

Abstract: Systems and processes for language identification from short strings are provided. In accordance with one example, a method includes, at a first electronic device with one or more processors and memory, receiving user input including an n-gram and determining a similarity between a representation of the n-gram and a representation of a first language. The representation of the first language is based on an occurrence of each of a plurality of n-grams in the first language and an occurrence of each of the plurality of n-grams in a second language. The method further includes determining whether the similarity between the representation of the n-gram and the representation of the first language satisfies a threshold.