Google Inc.

Jonathan Matthew Malmaud

Rishabh Singh

Manzil Zaheer

Navneet Potti

Sarah Fay Smith

Joel Galenson

Gabriel Rubow Culbertson

Runmin Zhao

Joey Hong

Nicolas Paul-Stringall Higuera

Giovanni De Toni

Jeff Hsu

Implementations are described herein for predicting symbolic transformation templates to automate source code transformations. In various implementations, pair(s) of predecessor and successor source code snippets may be processed using a symbolic transformation template prediction (STTP) model to predict a symbolic transformation template that includes a predecessor portion that matches the predecessor source code snippet(s) of the pair(s) and a successor portion that matches the successor source code snippet(s) of the pair(s). At least one additional predecessor source code snippet may be identified that matches the predecessor portion of the predicted symbolic transformation template. Placeholders of the predecessor portion of the predicted symbolic transformation template may be bound to one or more tokens of the at least one additional predecessor source code snippet to create binding(s). The successor portion of the predicted symbolic transformation template may be applied to the bindings to generate additional successor source code snippet(s).

Predicting and/or applying symbolic transformation templates

Techniques are described herein for iterative code generation using neural language models. In various implementations, an original source code snippet in a first programming language may be processed using a translation machine learning model to generate a first translation of the original source code snippet in a second programming language. The first translation of the original source code snippet may be evaluated to identify error(s) in the first translation. Based on the error(s), respective mask(s) may be inserted to generate a masked first translation of the original source code snippet in the second programming language. The masked first translation of the original source code snippet may be processed using the translation machine learning model to generate a second translation of the original source code snippet in the second language. The second translation may include infill(s) of corrected source code in place of one or more of the masks.

Iterative neural code translation

A server system obtains a transcription of content from a video and applies a machine learning resource to identify entities which are most likely to be searched for by a user viewing the video, based on the transcription of the content. The server system generates entity cards for each of the entities, each of the entity cards including descriptive content relating to a respective entity among the entities. The server system provides a user interface, to be displayed on a respective display of one or more user computing devices, for playing the video on a first portion of the user interface. When the video is played and a first entity among the entities is mentioned in the video, the user interface displays a first entity card on a second portion of the user interface, the first entity card including descriptive content relating to the first entity.

Entity cards including descriptive content relating to entities from a video

Growing community of inventors

Campbell, CA, United States of America

Jonathan Matthew Malmaud