We present a method for zero-shot, text-driven editing of natural images and videos. Given an image or video text prompt, our goal is to edit the appearance existing objects (e.g., texture) augment scene with visual effects smoke, fire) in semantic manner. train generator on internal dataset, extracted from single input, while leveraging external pretrained CLIP model impose losses. Rather than...

The paper discusses facilities of computer systems for editing scientific and technical texts, which partially automate functions of human editor and thus help the writer to improve text quality. Two experimental systems LINAR and CONUT developed in 90s to control the quality of Russian scientific and technical texts are briefly described; and general principles for designing more powerful edit...

Programming by example (PBE) literally means making “programs” from examples, but PBE techniques are also useful for automating text composition tasks by creating editing procedures from the history of a user’s editing operations. Composition by example (CBE) is a practical approach to improve the efficiency of text composition tasks using various simple PBE techniques. Thousands of people are ...

The paper presents new editing interface for lexicon of verb valencies (VerbaLex). Previous method of editing text files in custom setup of VIM text editor will be replaced by web application based on DEB platform. New interface will contain more strict control of the valencies format and structure. It should also be easier to learn for new editors. The data will be saved in XML format, thus al...

Simultaneous editing is a new method for automating repetitive text editing. After describing a set of regions to edit (the records), the user can edit any one record and see equivalent edits applied simultaneously to all other records. The essence of simultaneous editing is generalizing the user’s selection in one record to equivalent selections in the other records. We describe a generalizati...

Machine learning research has been very successful at producing powerful, broadlyapplicable classification learners. However, many practical learning problems do not fit the classification framework well, and as a result the initial phase of suitably formulating the problem and incorporating the relevant domain knowledge can be very difficult and typically consumes the majority of the project t...

This research examined the ability of an anthropomorphic interface assistant to help people learn and use an unfamiliar text-editing tool, with a specific focus on assessing proactive assistant behavior. Participants in the study were introduced to a text editing system that used keypress combinations for invoking the different editing operations. Participants then were directed to make a set o...

It is often assumed that raw MT output requires post-editing if it is to be used for more than gisting purposes. However, we know little about how end users engage with raw machine translated text or postedited text, or how usable this text is, in particular if users have to follow instructions and act on them. The research project described here measures the usability of raw machine translated...

Text editing exemplifies the type of computer application that exploits a computer’s nonnumerical capabilities and characteristics, specifically, its capability to store and di,splay data, handle abstract and complex data structures, and react immediately on command. Indeed, a steadily increasing degree of interactivity has characterized the development of new computer applications over the yea...