Improving Iterative Text Revision by Learning Where to Edit from Other
Revision Tasks
- URL: http://arxiv.org/abs/2212.01350v1
- Date: Fri, 2 Dec 2022 18:10:43 GMT
- Title: Improving Iterative Text Revision by Learning Where to Edit from Other
Revision Tasks
- Authors: Zae Myung Kim, Wanyu Du, Vipul Raheja, Dhruv Kumar, Dongyeop Kang
- Abstract summary: Iterative text revision improves text quality by fixing grammatical errors, rephrasing for better readability or contextual appropriateness, or reorganizing sentence structures throughout a document.
Most recent research has focused on understanding and classifying different types of edits in the iterative revision process from human-written text.
We aim to build an end-to-end text revision system that can iteratively generate helpful edits by explicitly detecting editable spans with their corresponding edit intents.
- Score: 11.495407637511878
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Iterative text revision improves text quality by fixing grammatical errors,
rephrasing for better readability or contextual appropriateness, or
reorganizing sentence structures throughout a document. Most recent research
has focused on understanding and classifying different types of edits in the
iterative revision process from human-written text instead of building accurate
and robust systems for iterative text revision. In this work, we aim to build
an end-to-end text revision system that can iteratively generate helpful edits
by explicitly detecting editable spans (where-to-edit) with their corresponding
edit intents and then instructing a revision model to revise the detected edit
spans. Leveraging datasets from other related text editing NLP tasks, combined
with the specification of editable spans, leads our system to more accurately
model the process of iterative text refinement, as evidenced by empirical
results and human evaluations. Our system significantly outperforms previous
baselines on our text revision tasks and other standard text revision tasks,
including grammatical error correction, text simplification, sentence fusion,
and style transfer. Through extensive qualitative and quantitative analysis, we
make vital connections between edit intentions and writing quality, and better
computational modeling of iterative text revisions.
Related papers
- K-Edit: Language Model Editing with Contextual Knowledge Awareness [71.73747181407323]
Knowledge-based model editing enables precise modifications to the weights of large language models.
We present K-Edit, an effective approach to generating contextually consistent knowledge edits.
arXiv Detail & Related papers (2025-02-15T01:35:13Z) - ParaRev: Building a dataset for Scientific Paragraph Revision annotated with revision instruction [26.64363135181992]
We explore the impact of shifting from sentence-level to paragraph-level scope for the task of scientific text revision.
The paragraph level definition of the task allows for more meaningful changes, and is guided by detailed revision instructions rather than general ones.
Our experiments demonstrate that using detailed instructions significantly improves the quality of automated revisions compared to general approaches.
arXiv Detail & Related papers (2025-01-09T13:19:55Z) - WikiIns: A High-Quality Dataset for Controlled Text Editing by Natural
Language Instruction [56.196512595940334]
We build and release WikiIns, a high-quality controlled text editing dataset with improved informativeness.
With the high-quality annotated dataset, we propose automatic approaches to generate a large-scale silver'' training set.
arXiv Detail & Related papers (2023-10-08T04:46:39Z) - XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates [7.660511135287692]
This paper introduces XATU, the first benchmark specifically designed for fine-grained instruction-based explainable text editing.
XATU considers finer-grained text editing tasks of varying difficulty, incorporating lexical, syntactic, semantic, and knowledge-intensive edit aspects.
We demonstrate the effectiveness of instruction tuning and the impact of underlying architecture across various editing tasks.
arXiv Detail & Related papers (2023-09-20T04:58:59Z) - EditEval: An Instruction-Based Benchmark for Text Improvements [73.5918084416016]
This work presents EditEval: An instruction-based, benchmark and evaluation suite for automatic evaluation of editing capabilities.
We evaluate several pre-trained models, which shows that InstructGPT and PEER perform the best, but that most baselines fall below the supervised SOTA.
Our analysis shows that commonly used metrics for editing tasks do not always correlate well, and that optimization for prompts with the highest performance does not necessarily entail the strongest robustness to different models.
arXiv Detail & Related papers (2022-09-27T12:26:05Z) - Towards Automated Document Revision: Grammatical Error Correction,
Fluency Edits, and Beyond [46.130399041820716]
We introduce a new document-revision corpus, TETRA, where professional editors revised academic papers sampled from the ACL anthology.
We show the uniqueness of TETRA compared with existing document revision corpora and demonstrate that a fine-tuned pre-trained language model can discriminate the quality of documents after revision even when the difference is subtle.
arXiv Detail & Related papers (2022-05-23T17:37:20Z) - Text Revision by On-the-Fly Representation Optimization [76.11035270753757]
Current state-of-the-art methods formulate these tasks as sequence-to-sequence learning problems.
We present an iterative in-place editing approach for text revision, which requires no parallel data.
It achieves competitive and even better performance than state-of-the-art supervised methods on text simplification.
arXiv Detail & Related papers (2022-04-15T07:38:08Z) - Understanding Iterative Revision from Human-Written Text [10.714872525208385]
IteraTeR is the first large-scale, multi-domain, edit-intention annotated corpus of iteratively revised text.
We better understand the text revision process, making vital connections between edit intentions and writing quality.
arXiv Detail & Related papers (2022-03-08T01:47:42Z) - Text Editing by Command [82.50904226312451]
A prevailing paradigm in neural text generation is one-shot generation, where text is produced in a single step.
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.
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.
arXiv Detail & Related papers (2020-10-24T08:00:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.