Abstract: Systems and processes for operating an intelligent automated assistant are provided. In one example process a set of words including a grammatical error is received. The process can generate, using a neural network based on the set of words including the grammatical error and a reference set of words, a transformed set of words and further determine, based on the set of words including the grammatical error and the reference set of words, a reconstructed reference set of words. The process can also determine, based on a comparison of the transformed set of words and the reconstructed reference set of words, whether the transformed set of words is grammatically correct and provide an indication of whether the transformed set of words is grammatically correct to the neural network.

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 presenting content in a first application. At least a portion of the content is presented without requiring input from a user. The method further includes receiving a request to open a second application. In response to receiving the request, the second application is presented with an input-receiving field. Before receiving any user input at the input-receiving field, a selectable user interface object is displayed with an indication that the portion of the content was viewed in the first application, allowing the user to paste at least the portion of the content into the input-receiving field. In response to detecting a selection of the selectable user interface object, the portion of the content is pasted into the input-receiving field.

Abstract: An example process for recognizing handwritten input includes obtaining input data representing handwritten input, where the handwritten input is associated with a first dimension and a second dimension relative to the handwritten input; sampling the input data to obtain a plurality of coordinates representing the handwritten input; determining, based on the plurality of coordinates, a sequence of vectors representing a respective plurality of portions of the handwritten input, where: each portion of the respective plurality of portions is associated with a respective height and width corresponding respectively to the first and second dimensions, the respective height being greater than the respective width; and consecutive vectors of the sequence of vectors represent respective consecutive portions of the handwritten input; generating, using a handwriting recognition model, based on the sequence of vectors, one or more characters for the handwritten input; and causing the one or more characters to be display

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 modifying word predictions are provided. In one example, a user input is received including one or more words. A prediction of a word sequence corresponding to one or more words is obtained, and context information associated with the word sequence is obtained. In accordance with a determination, based on the context information, that the prediction of the word sequence corresponds to a predetermined semantic reference, the prediction of the word sequence is modified, and an output is provided corresponding to the modified prediction of the word sequence. In accordance with a determination, based on the context information, that the prediction of the word sequence does not correspond to a predetermined semantic reference, an output is provided corresponding to the prediction of the word sequence.

Abstract: Techniques for predicting sentiment from textual data are described herein. In some examples, the described techniques utilize a sentiment prediction model having bidirectional long short-term memory (LSTM) networks with one or more convolution-and-pooling stages. The bidirectional LSTM networks process vector representations of words in a textual word sequence to determine forward and backward word-level context feature vectors. Forward and backward phrase-level feature vectors are determined based on the forward and backward word-level context feature vectors. The one or more convolution-and-pooling stages pool the forward and backward phrase-level feature vectors to determine pooled phrase-level feature vectors. A sentiment representing the textual word sequence is determined based on the pooled phrase-level feature vectors.

Abstract: Systems and processes for unified language modeling are provided. In accordance with one example, a method includes, at an electronic device with one or more processors and memory, receiving a character of a sequence of characters and determining a current character context based on the received character of the sequence of characters and a previous character context. The method further includes determining a current word representation based on the current character context and determining a current word context based on the current word representation and a previous word context. The method further includes determining a next word representation based on the current word context and providing the next word representation.

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 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: An example method includes at an electronic device with one or more processors and memory: obtaining first data representing a user-generated keyboard path for one or more words; obtaining second data representing a synthetic keyboard path for the one or more words; generating, using a first instance of a generative network, based on the first data and the second data, third data representing a modification of the synthetic keyboard path; determining whether the third data represent a second user-generated keyboard path; determining whether the third data represent the one or more words; and in accordance with a determination that the third data represent a second user-generated keyboard path and a determination that the third data represent the one or more words: training a model for keyboard path recognition based on the third data.

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 obtaining information identifying a first physical location viewed by a user in a first application. The method further includes detecting a first input. In response to detecting the first input: a second application is identified that is capable of accepting geographic location information; and an affordance is presented that is distinct from the first application, with a suggestion to open the second application. The suggestion includes information about the first physical location. The method further includes detecting a second input at the affordance. In response to detecting the second input at the affordance, the second application is opened and populated to include information that is based at least in part on the information identifying the first physical location.

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 obtaining information identifying a first physical location viewed by a user in a first application. The method further includes detecting a first input. In response to detecting the first input: a second application is identified that is capable of accepting geographic location information; and an affordance is presented that is distinct from the first application, with a suggestion to open the second application. The suggestion includes information about the first physical location. The method further includes detecting a second input at the affordance. In response to detecting the second input at the affordance, the second application is opened and populated to include information that is based at least in part on the information identifying the first physical location.

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 presenting content in a first application. At least a portion of the content is presented without requiring input from a user. The method further includes receiving a request to open a second application. In response to receiving the request, the second application is presented with an input-receiving field. Before receiving any user input at the input-receiving field, a selectable user interface object is displayed with an indication that the portion of the content was viewed in the first application, allowing the user to paste at least the portion of the content into the input-receiving field. In response to detecting a selection of the selectable user interface object, the portion of the content is pasted into the input-receiving field.

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: 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 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: Techniques for predicting sentiment from textual data are described herein. In some examples, the described techniques utilize a sentiment prediction model having bidirectional long short-term memory (LSTM) networks with one or more convolution-and-pooling stages. The bidirectional LSTM networks process vector representations of words in a textual word sequence to determine forward and backward word-level context feature vectors. Forward and backward phrase-level feature vectors are determined based on the forward and backward word-level context feature vectors. The one or more convolution-and-pooling stages pool the forward and backward phrase-level feature vectors to determine pooled phrase-level feature vectors. A sentiment representing the textual word sequence is determined based on the pooled phrase-level feature vectors.

Abstract: Systems and processes for operating an intelligent automated assistant are provided. In one example process, one or more input words can be received. The process can extract, based on the one or more input words, seed data for unsupervised training of a first learning network. Training data that includes a collection of words having typographical errors for the first learning network can be obtained. The process can determine, using the first learning network and based on the seed data and the training data, one or more output words having a probability distribution corresponding to a probability distribution of the training data. The one or more output words can include typographical errors. The process can generate, based on the determined one or more output words, a data set for supervised training of a second learning network. The second learning network can provide one or more typographical error suggestions.

Abstract: Systems and processes for multilingual word prediction are provided. In accordance with one example, a method includes, at an electronic device having one or more processors and memory, identifying context information of the electronic device and generating, with the one or more processors, a plurality of candidate words based on the context information, wherein a first candidate word of the plurality of candidate words corresponds to a first language of a plurality of languages and a second candidate word of the plurality of candidate words corresponds to a second language of the plurality of languages different than the first language.