Diamonds in the Rough: Generating Fluent Sentences from Early-Stage Drafts for Academic Writing Assistance

Ito, Toshiro; Kuribayashi, Tatsuki; Kobayashi, Hayato; Brassard, Ana; Hagiwara, Masato; Suzuki, Jun; Inui, Kentaro

doi:10.18653/v1/w19-8606

Cited by 14 publications

(12 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to this is Grammatical Error Correction which seeks to correct errors such as grammar and punctuation (Ng et al, 2014;. Sentence revision (Ito et al, 2019) extends this to cases for which major rewriting may be needed. Sentence simplification (Nisioi et al, 2017) aims at using techniques such as shortening the sentences to make a text more readable.…”

Section: Sentence Editing and Simplificationmentioning

confidence: 99%

Sound Natural: Content Rephrasing in Dialog Systems

Einolghozati

Gupta

Diedrick

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

We introduce a new task of rephrasing for a more natural virtual assistant. Currently, virtual assistants work in the paradigm of intentslot tagging and the slot values are directly passed as-is to the execution engine. However, this setup fails in some scenarios such as messaging when the query given by the user needs to be changed before repeating it or sending it to another user. For example, for queries like 'ask my wife if she can pick up the kids' or 'remind me to take my pills', we need to rephrase the content to 'can you pick up the kids' and 'take your pills'. In this paper, we study the problem of rephrasing with messaging as a use case and release a dataset of 3000 pairs of original query and rephrased query. We show that BART, a pre-trained transformers-based masked language model with auto-regressive decoding, is a strong baseline for the task, and show improvements by adding a copy-pointer and copy loss to it. We analyze different tradeoffs of BART-based and LSTM-based seq2seq models, and propose a distilled LSTM-based seq2seq as the best practical model.

show abstract

Section: Sentence Editing and Simplificationmentioning

confidence: 99%

Sound Natural: Content Rephrasing in Dialog Systems

Einolghozati

Gupta

Diedrick

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…Previous works on iterative text revision have three major limitations: (1) simplifying the task to an noniterative "original-to-final" text paraphras-ing; (2) focusing largely on sentence-level editing Botha et al, 2018;Ito et al, 2019;Faltings et al, 2021); (3) developing editing taxonomies within individual domains (e.g. Wikipedia articles, academic writings) (Yang et al, 2017;Zhang et al, 2017;Anthonio et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

“…2 Related Work and how effective their actions are (Yang et al, 2017;Zhang et al, 2017;Ito et al, 2019). However, these works do not further explore how to leverage edit intentions to generate better-revised documents.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Understanding Iterative Revision from Human-Written Text

Du¹,

Raheja²,

Kumar³

et al. 2022

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Writing is, by nature, a strategic, adaptive, and more importantly, an iterative process. A crucial part of writing is editing and revising the text. Previous works on text revision have focused on defining edit intention taxonomies within a single domain or developing computational models with a single level of edit granularity, such as sentence-level edits, which differ from human's revision cycles. This work describes ITERATER: the first largescale, multi-domain, edit-intention annotated corpus of iteratively revised text. In particular, ITERATER is collected based on a new framework to comprehensively model the iterative text revisions that generalize to various domains of formal writing, edit intentions, revision depths, and granularities. When we incorporate our annotated edit intentions, both generative and edit-based text revision models significantly improve automatic evaluations. 1 Through our work, we better understand the text revision process, making vital connections between edit intentions and writing quality, enabling the creation of diverse corpora to support computational modeling of iterative text revisions. * This research was performed when Wanyu Du was interning at Grammarly.1 Code and dataset are available at https://github. com/vipulraheja/IteraTeR. 7 https://www.ctan.org/pkg/latexdiff 8 https://github.com/zaemyung/sentsplit 9 We also record character-level indices of their positions within the original sentence and the paragraph.

show abstract

“…Computational modeling of the iterative text revision process is essential for building intelligent and interactive writing assistants. Most prior works on the development of neural text revision systems 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. The direct application of such revision systems in an iterative way, however, could generate some "noisy" edits and require much burden on human writers to fix the noise.…”

Section: Introductionmentioning

confidence: 99%

Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision

Du¹,

Myung²,

Raheja³

et al. 2022

Proceedings of the First Workshop on Intelligent and Interactive Writing Assistants (In2Writing 2022)

View full text Add to dashboard Cite

Revision is an essential part of the human writing process. It tends to be strategic, adaptive, and, more importantly, iterative in nature. Despite the success of large language models on text revision tasks, they are limited to non-iterative, one-shot revisions. Examining and evaluating the capability of large language models for making continuous revisions and collaborating with human writers is a critical step towards building effective writing assistants. In this work, we present a human-inthe-loop iterative text revision system, Read, Revise, Repeat (R3), which aims at achieving high quality text revisions with minimal human efforts by reading model-generated revisions and user feedbacks, revising documents, and repeating human-machine interactions. In R3, a text revision model provides text editing suggestions for human writers, who can accept or reject the suggested edits. The accepted edits are then incorporated into the model for the next iteration of document revision. Writers can therefore revise documents iteratively by interacting with the system and simply accepting/rejecting its suggested edits until the text revision model stops making further revisions or reaches a predefined maximum number of revisions. Empirical experiments show that R3 can generate revisions with comparable acceptance rate to human writers at early revision depths, and the human-machine interaction can get higher quality revisions with fewer iterations and edits. The collected human-model interaction dataset and system code are available at https://github. com/vipulraheja/IteraTeR. Our system demonstration is available at https:// youtu.be/lK08tIpEoaE.

show abstract

Diamonds in the Rough: Generating Fluent Sentences from Early-Stage Drafts for Academic Writing Assistance

Cited by 14 publications

References 31 publications

Sound Natural: Content Rephrasing in Dialog Systems

Sound Natural: Content Rephrasing in Dialog Systems

Understanding Iterative Revision from Human-Written Text

Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision

Contact Info

Product

Resources

About