Text Editing by Command

By Felix Faltings, Michel Galley, Gerold Hintz, Chris Brockett, Chris Quirk, Jianfeng Gao, Bill Dolan. 2020

44 citations recorded by the source corpus.

A prevailing paradigm in neural text generation is one-shot generation, where text is produced in a single step. The one-shot setting is inadequate, however, when the constraints the user wishes to impose on the generated text are dynamic, especially when authoring longer documents. We address this limitation with an interactive text generation setting in which the user interacts with the system by issuing commands to edit existing text. To this end, we propose a novel text editing task, and introduce WikiDocEdits, a dataset of single-sentence edits crawled from Wikipedia. We show that our Interactive Editor, a transformer-based model trained on this dataset, outperforms baselines and obtains positive results in both automatic and human evaluations. We present empirical and qualitative analyses of this model’s performance.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

PEER: A Collaborative Language Model (2022, methodology): “Similar to prior work on text editing (Faltings et al., 2021; Reid and Neubig, 2022), our first step in overcoming this issue is turning to Wikipedia – a single source that comes close to fulfilling all our needs: It provides a full edit history including comments on a diverse set of topics, is larg”
Automatic Document Sketching: Generating Drafts from Analogous Texts (2021, background): “Kannan et al., 2016; Alikaniotis and Raheja, 2019; Prabhumoye et al., 2019; Faltings et al., 2021).”
Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision (2022, background): “Most prior works on the development of neural text revision systems (Faruqui et al., 2018; Botha et al., 2018; Ito et al., 2019; Faltings et al., 2021) do not take the iterative nature of text revision and human feedback on suggested revisions into consideration.”
Generating Sequences by Learning to Self-Correct (2022, background): “Self-correction relates to recent works on editing text, including modeling Wikipedia edits (Reid & Neubig, 2022; Faltings et al., 2021; Schick et al., 2022), which relies on supervised edits, unsupervised methods (Miao et al., 2019; Liu et al., 2020) that perturb sequences with simple operations…”
Understanding Iterative Revision from Human-Written Text (2022, methodology): “ing; (2) focusing largely on sentence-level editing (Faruqui et al., 2018; Botha et al., 2018; Ito et al., 2019; Faltings et al., 2021); (3) developing editing taxonomies within individual domains (e.”
Learning to Model Editing Processes (2022, methodology): “We then curate these comments and develop a dataset for usage on downstream tasks—for both edit summary generation (Loyola et al., 2017) and edit-summary-conditioned text editing (Faltings et al., 2021).”