Abstract: A constrained decoding technique incorporates token constraints into a beam search at each time step of a decoding process in order to generate viable candidate sequences that are syntactically and semantically correct. The token constraints identify source code tokens or sequences of tokens that should appear in a candidate sequence. The token constraints are generated from checking whether a token predicted at each decoding step is feasible for a partial solution based on the production rules of the grammar of the programming language, the syntactic correctness of a partial sequence, and/or static type correctness.

Abstract: Techniques for mapping size information associated with a client to target brands, garments, sizes, shapes, and styles for which there is no standardized correlation. The size information associated with a client may be generated by modeling client garments, accessing computer aided drawing (CAD) files associated with client garments, or by analyzing a history of garment purchases associated with the client. Information for target garments may be generated in a similar fashion. A system may then create a standardized scale with a set of sizes for a target, and map a client base size to that standardized size scale. Similar matching and mapping may also be done with shape and style considerations. A recommendation based on the mapping may then be communicated to the client.

Abstract: A system to provide image processing services responsive to requests including image data includes a system layer that forwards a request to an image application processing interface. Image processing provides an image comparison, barcode recognition, and optical character recognition. The image processing compares the image data to products in a database in order to identify a matching product. The system layer receives the matching information and forwards to a user.

Abstract: The syntax elements of a source code program used to represent the context of a focal method are selected based on a priority order. The selected syntax elements are input into a fixed-size context window that is used to train a neural transformer with attention model to learn to generate source code and used by the neural transformer model to generate source code. The context window contains prioritized sequences of tokens that extend beyond the target focus in order to provide a longer visibility back into the source code program for the model to learn predictive patterns. This gives the model a file-level context of the source code program without increasing the size of the context window.

Abstract: A code review process utilizes a deep learning model trained on historical code reviews to automatically perform peer or code review of a source code file. The deep learning model is able to predict the code reviews relevant to a source code snippet by learning from historical code reviews. The deep learning model is trained on pairs of code snippets and code reviews that are relevant to each other and pairs of code snippets and code reviews that have no relation to each other. The deep learning model is data driven thereby not relying on pre-configured rules which makes the model adaptable to different review environments.

Abstract: A natural language code search service provides idioms or frequently-occurring code patterns for a code fragment based on similar type usage and method/API invocation usage. The search service uses a data mining technique that mines code snippets found from various websites and code snippets generated from a neural model to detect idioms in the code snippets that were previously unknown and which can be reused. A search is initiated through a natural language query within a code development tool or application thereby avoiding the need to switch out of the current application to perform the search.

Abstract: An automated system for resolving program merges uses a multi-task neural transformer with attention. Each component of a merge conflict tuple (A, B, O) is represented as an AST and transformed into aligned AST-node sequences and aligned editing sequences. The multi-task neural transformer model predicts the tree editing steps needed to resolve the merge conflict and applies them to the AST representation of the code base. The tree editing steps include the edit actions that needed to be applied to the AST of the code base and the edit labels that are inserted or updated with the edit actions.

Abstract: An automated system for resolving program merges uses a multi-task neural transformer with attention. Each component of a merge conflict tuple (A, B, O) is represented as an AST and transformed into aligned AST-node sequences and aligned editing sequences. The multi-task neural transformer model predicts the tree editing steps needed to resolve the merge conflict and applies them to the AST representation of the code base. The tree editing steps include the edit actions that needed to be applied to the AST of the code base and the edit labels that are inserted or updated with the edit actions.

Abstract: In one embodiment, a method is illustrated as including defining a set of perspective objects capable of being placed onto a modified web page, monitoring parameters of a web page, the parameters including a number of times a current object is executed on the web page, using an Artificial Intelligence (AI) algorithm to determine a perspective object with a preferred Return On Investment (ROI), and selecting the perspective object to be placed onto the modified web page.

Abstract: In various example embodiments, a system and method for using camera metadata for making recommendations are presented. At least one image file having camera metadata is received. The camera metadata of the at least one image file is analyzed to determine improvements to image capture aspects associated with the at least one image file. Feedback related to the improvements to the image capture aspects associated with the at least one image file is generated. In some embodiments, the feedback may be used to generate camera and other product upgrade recommendations.

Abstract: A system, computer-readable storage medium storing at least one program, and computer-implemented method for providing recommendations based on social network sharing activity. Sharing activity relating to the sharing of the content item on a social network by a first user is accessed. Consumption information related to the consumption of the content item. A correlation between the sharing activity and the consumption information is determined. A recommendation is then generated based on the correlation.

Abstract: A deep learning model is quantized during its training to perform a target software engineering task. During training, a portion of the full-precision floating point weights is quantized into INT4 or INT 8 data types through scalar quantization or product quantization to make the model more resilient to quantization and to reduce the noise between the quantized and full-precision model outputs. In scalar quantization, each sub-block consists of a single weight that is mapped into a codeword of a codebook. In product quantization, an identity matrix and a codebook of centroids is used to map a quantized weight into its original value.

Abstract: A method and a system for providing recommendations based on branding are disclosed. In example embodiments, an index comprising predetermined brand relationships is maintained. Each predetermined brand relationship comprises a first brand, a second brand, and a recommendation score between the first brand and the second brand. A corpus containing a plurality of user queries is also maintained. A seed set of brands corresponding to a category in the index is expanded by accessing the corpus containing the plurality of user queries, evaluating user queries of the plurality of user queries that contain a disjunction of brand terms, and identifying a new brand to add to the seed set based on the evaluating.

Abstract: A neural transformer model with attention is trained to predict candidates to complete a line of source code with a zero-inference capability. The model is trained on an unsupervised training dataset that includes features from source code written in multiple programming languages. The features include a file-level context and a local context, where the file-level context includes a global context, a class context, a function context, and/or a method context for each class, function and/or method of the source code programs used in the training dataset. The local context includes method bodies, function bodies, and/or stand-alone code of main method routines. From these features, the model is able to learn to predict an ordered sequence of code elements that complete a line of source code in a programming language seen and not seen during training.

Abstract: Systems and methods for on demand local commerce are described. One example embodiment includes a device gathering location information and product interest associated with clients and client devices. The system may use location information in determining that the first plurality of client devices are within a first geographic area during a first time period, and may further use the interest information in calculating an interest level for a first product. A threshold may be identified and used in determining that the interest level for the first product exceeds the threshold. When the calculated interest level exceeds the threshold, a local commerce action is initiated. In various embodiments, the local commerce action may be a live on demand auction at a particular location, an offer associated with a geofenced area, a sales location recommendation to a merchant, or any other such local commerce action.

Abstract: A deep learning model trained to learn to predict source code is tuned for a target source code generation task through reinforcement learning using a reward score that considers the quality of the source code predicted during the tuning process. The reward score is adjusted to consider code-quality factors and source code metrics. The code-quality factors account for the predicted source code having syntactic correctness, successful compilation, successful execution, successful invocation, readability, functional correctness, and coverage. The source code metrics generate a score based on how close the predicted source code is to a ground truth code.

Abstract: An automated program repair system uses a neural transformer model with attention to predict a bug-free version of a method having a source code bug identified in an associated stack trace. The neural transformer model is pre-trained with English language text and the source code of a target programming language. The pre-trained neural transformer model is trained to create synthetic bugs in bug-free methods. The bug-free methods with the synthetic bugs are executed with a test case to obtain a stack trace of the source code bug. The method with the synthetic bug, without the bug, and its stack trace are used to train the neural transformer model to predict repairs for buggy methods.

Abstract: An apparatus and method to adjust item recommendations are disclosed herein. A first image attribute of a query image is compared to a second image attribute of each of a plurality of inventory images of a plurality of inventory items to identify the inventory items similar to the query image. Item recommendations comprising the identified inventory items in a first listing order are provided for display at a remote device. A second listing order of the identified inventory items is determined based on a user preference for a particular one of the identified inventory items. At least the second listing order is provided to the remote device for re-display of the item recommendations in accordance with the second listing order.

Abstract: Techniques for generating a digital wardrobe are presented herein. A transceiver can be configured to receive a request having a garment identifier and a user identifier. Additionally, an access module can be configured to access a first garment model, access a body model of the user corresponding to the user identifier, and access a second garment model corresponding to the user identifier. Furthermore, a processor can be configured by a garment simulation module to position the body model inside the first garment model and the second garment model, and calculate simulated forces based on the positioning. Moreover, a rendering module can be configured to generate an image of the garment models draped on the body model based on the calculated simulated forces. Subsequently, a display module can be configured to cause presentation of the generated image on a display of a device.

Abstract: Generally discussed herein are devices, systems, and methods for generating an automatic interactive digital notebook completion model. A method can include receiving notebook content of an interactive digital notebook, the notebook content including a markdown cell followed by a code cell. The method can include generating input/output examples by, for each input/output example by masking one of (i) content of the markdown cell or (ii) content of the code cell resulting in a masked cell, identifying the masked cell and content of another cell of the markdown cell or the code that is not masked as an input for an input/output example, and identifying the content of the masked cell as an output for the input/output example. The method can include training, based on the input/output examples, a natural language processing model that generates a prediction of the content of a second masked cell as an output.