Text Editing by Command

Faltings, Felix; Galley, Michel; Hintz, Gerold; Brockett, Chris; Quirk, Chris; Gao, Jianfeng; Dolan, Bill

doi:10.18653/v1/2021.naacl-main.414

Cited by 17 publications

(25 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To simplify this problem, we employ the n-th order Markov assumption, assuming that the probability of the next document is conditioned only on the previous n documents p(x i |x i−1 i−n ). This probability could be modeled directly, and in fact in the case of n = 1 this becomes analogous to the single-step editing problem tackled by previous work (Yin et al, 2019a;Malmi et al, 2019;Reid and Zhong, 2021;Faltings et al, 2021). To our knowledge, no previous work has modeled natural editing processes with n > 1.…”

Section: Modeling Operations Andmentioning

confidence: 87%

“…When extracting each edit we keep the edit summary (akin to a commit message) supplied by the editor at time of editing. 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-summaryconditioned text editing (Faltings et al, 2021).…”

Section: Wikirevisionsmentioning

confidence: 99%

“…positive vs negative) can be relatively minimal (Reid and Zhong, 2021;Mallinson et al, 2020). Furthermore, Faltings et al (2021) explored natural language conditioned editing as a means for controllable text generation using a T5-based (Raffel et al, 2020) sequence to sequence model. Also related to our work is text morphing (Huang et al, 2018), in which they look at an edit-based model to interpolate between two sentences.…”

Section: Human Evaluationmentioning

confidence: 99%

“…The proposed multi-step editing model predicts discrete edit operations (Levenshtein, 1966) to en-able progressive refinement as shown in Figure 1, rather than framing sequence editing as a sequence to sequence task (Reid and Zhong, 2021;Faltings et al, 2021). In the figure, for each step of the editing process discrete operations (insert, replace, delete, keep) are predicted and then actions (such as generating a replaced span) are performed based on this.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Learning to Model Editing Processes

Reid¹,

Neubig²

2022

Preprint

View full text Add to dashboard Cite

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 introduced edit-based models for various tasks (such as neural machine translation and text style transfer), but these generally model a single edit step. In this work, we propose modeling editing processes, modeling the whole process of iteratively generating sequences. We form a conceptual framework to describe the likelihood of multi-step edits, and describe neural models that can learn a generative model of sequences based on these multistep edits. We introduce baseline results and metrics on this task, finding that modeling editing processes improves performance on a variety of axes on both our proposed task and related downstream tasks compared to previous single-step models of edits. 1

show abstract

Section: Modeling Operations Andmentioning

confidence: 87%

Section: Wikirevisionsmentioning

confidence: 99%

Section: Human Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning to Model Editing Processes

Reid¹,

Neubig²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Experimental results on four tasks demonstrate the effectiveness of LEMON: the execution-guided pre-training strategy brings significant improvements on all of them and LEMON achieves the state-of-the-art performance on three of them. For future work, we hope to extend our approach to more complex environments and tasks such as image editing (Fu et al, 2020) and text editing (Faltings et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-training

Shi¹,

Liu²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Language-based environment manipulation requires agents to manipulate the environment following natural language instructions, which is challenging due to the huge space of the environments. To address this challenge, various approaches have been proposed in recent work. Although these approaches work well for their intended environments, they are difficult to generalize across environments. In this work, we propose LEMON, a general framework for language-based environment manipulation tasks. Specifically, we first propose a unified approach to deal with various environments using the same generative language model. Then we propose an execution-guided pre-training strategy to inject prior knowledge of environments to the language model with a pure synthetic pre-training corpus. Experimental results on tasks including ALCHEMY, SCENE, TANGRAMS and PROPARA demonstrate the effectiveness of LEMON: it achieves new state-of-the-art results on ALCHEMY, SCENE and PROPARA, and the execution-guided pretraining strategy brings remarkable improvements on all experimental tasks.

show abstract