Related papers: Text Editing as Imitation Game

Users interact with text, image, code, or other editors on a daily basis. However, machine learning models are rarely trained in the settings that reflect the interactivity between users and their editor. This is understandable as training…

We propose a framework for training non-autoregressive sequence-to-sequence models for editing tasks, where the original input sequence is iteratively edited to produce the output. We show that the imitation learning algorithms designed to…

We propose LaserTagger - a sequence tagging approach that casts text generation as a text editing task. Target texts are reconstructed from the inputs using three main edit operations: keeping a token, deleting it, and adding a phrase…

Large pre-trained language models have recently been expanded and applied to programming language tasks with great success, often through further pre-training of a strictly-natural language model--where training sequences typically contain…

Text-based image editing is typically approached as a static task that involves operations such as inserting, deleting, or modifying elements of an input image based on human instructions. Given the static nature of this task, in this…

Text revision refers to a family of natural language generation tasks, where the source and target sequences share moderate resemblance in surface form but differentiate in attributes, such as text formality and simplicity. Current…

Neural sequence-to-sequence models are finding increasing use in editing of documents, for example in correcting a text document or repairing source code. In this paper, we argue that common seq2seq models (with a facility to copy single…

In neural text editing, prevalent sequence-to-sequence based approaches directly map the unedited text either to the edited text or the editing operations, in which the performance is degraded by the limited source text encoding and long,…

Most existing sequence generation models produce outputs in one pass, usually left-to-right. However, this is in contrast with a more natural approach that humans use in generating content; iterative refinement and editing. Recent work has…

In this work, we introduce a self-supervised behavior cloning transformer for text games, which are challenging benchmarks for multi-step reasoning in virtual environments. Traditionally, Behavior Cloning Transformers excel in such tasks…

Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, simplification, and style transfer. These tasks share a common trait - they…

Imitation learning aims to extract high-performance policies from logged demonstrations of expert behavior. It is common to frame imitation learning as a supervised learning problem in which one fits a function approximator to the…

We propose Seq2Edits, an open-vocabulary approach to sequence editing for natural language processing (NLP) tasks with a high degree of overlap between input and output texts. In this approach, each sequence-to-sequence transduction is…

Text editing frames grammatical error correction (GEC) as a sequence tagging problem, where edit tags are assigned to input tokens, and applying these edits results in the corrected text. This approach has gained attention for its…

Despite the widely successful applications, bootstrapping and fine-tuning semantic parsers are still a tedious process with challenges such as costly data annotation and privacy risks. In this paper, we suggest an alternative,…

Extracting action sequences from natural language texts is challenging, as it requires commonsense inferences based on world knowledge. Although there has been work on extracting action scripts, instructions, navigation actions, etc., they…

Natural language is perhaps the most flexible and intuitive way for humans to communicate tasks to a robot. Prior work in imitation learning typically requires each task be specified with a task id or goal image -- something that is often…

The task of Grammatical Error Correction (GEC) has received remarkable attention with wide applications in Natural Language Processing (NLP) in recent years. While one of the key principles of GEC is to keep the correct parts unchanged and…

While most neural generative models generate outputs in a single pass, the human creative process is usually one of iterative building and refinement. Recent work has proposed models of editing processes, but these mostly focus on editing…

Recent neural approaches to data-to-text generation have mostly focused on improving content fidelity while lacking explicit control over writing styles (e.g., word choices, sentence structures). More traditional systems use templates to…