# Automatic Document Sketching: Generating Drafts from Analogous Texts

arXiv: https://arxiv.org/abs/2106.07192 · HTML: https://mlsanity.com/paper/2106.07192/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 57 references that are in the map.
- First posted on arXiv 14 Jun 2021.

## Builds on (most cited first, 30 of 34)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [Asking and Answering Questions to Evaluate the Factual Consistency of Summaries](https://mlsanity.com/paper/2004.04228/) (2020)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://mlsanity.com/paper/1804.06437/) (2018)
- [Hierarchical Transformers for Multi-Document Summarization](https://mlsanity.com/paper/1905.13164/) (2019)
- [Correcting Length Bias in Neural Machine Translation](https://mlsanity.com/paper/1808.10006/) (2018)
- [PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking](https://mlsanity.com/paper/2004.14967/) (2020)
- [Gmail Smart Compose: Real-Time Assisted Writing](https://mlsanity.com/paper/1906.00080/) (2019)
- [Toxicity Detection: Does Context Really Matter?](https://mlsanity.com/paper/2006.00998/) (2020)
- [Generating Sentences by Editing Prototypes](https://mlsanity.com/paper/1709.08878/) (2017)
- [Multi-Reward Reinforced Summarization with Saliency and Entailment](https://mlsanity.com/paper/1804.06451/) (2018)
- [A Retrieve-and-Edit Framework for Predicting Structured Outputs](https://mlsanity.com/paper/1812.01194/) (2018)
- [Learning Neural Templates for Text Generation](https://mlsanity.com/paper/1808.10122/) (2018)
- [Smart Reply: Automated Response Suggestion for Email](https://mlsanity.com/paper/1606.04870/) (2016)
- [Deep Communicating Agents for Abstractive Summarization](https://mlsanity.com/paper/1803.10357/) (2018)
- [In-IDE Code Generation from Natural Language: Promise and Challenges](https://mlsanity.com/paper/2101.11149/) (2021)
- [Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering](https://mlsanity.com/paper/2004.11892/) (2020)
- [Text Editing by Command](https://mlsanity.com/paper/2010.12826/) (2020)
- [Text Generation with Exemplar-based Adaptive Decoding](https://mlsanity.com/paper/1904.04428/) (2019)
- [Reinforced Video Captioning with Entailment Rewards](https://mlsanity.com/paper/1708.02300/) (2017)
- [Contrastive Multi-document Question Generation](https://mlsanity.com/paper/1911.03047/) (2019)
- [How to Write Summaries with Patterns? Learning towards Abstractive Summarization through Prototype Editing](https://mlsanity.com/paper/1909.08837/) (2019)
- [Towards Content Transfer through Grounded Text Generation](https://mlsanity.com/paper/1905.05293/) (2019)
- [Low-Resource Response Generation with Template Prior](https://mlsanity.com/paper/1909.11968/) (2019)

## Built on by (most cited first, 4 of 4)

- [PEER: A Collaborative Language Model](https://mlsanity.com/paper/2208.11663/) (2022)
- [A Design Space for Intelligent and Interactive Writing Assistants](https://mlsanity.com/paper/2403.14117/) (2024)
- [CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning](https://mlsanity.com/paper/2112.08558/) (2021)
- [CASIMIR: A Corpus of Scientific Articles enhanced with Multiple Author-Integrated Revisions](https://mlsanity.com/paper/2403.00241/) (2024)

## Abstract (arXiv)

The advent of large pre-trained language models has made it possible to make high-quality predictions on how to add or change a sentence in a document. However, the high branching factor inherent to text generation impedes the ability of even the strongest language models to offer useful editing suggestions at a more global or document level. We introduce a new task, document sketching, which involves generating entire draft documents for the writer to review and revise. These drafts are built from sets of documents that overlap in form - sharing large segments of potentially reusable text - while diverging in content. To support this task, we introduce a Wikipedia-based dataset of analogous documents and investigate the application of weakly supervised methods, including use of a transformer-based mixture of experts, together with reinforcement learning. We report experiments using automated and human evaluation methods and discuss relative merits of these models.