# A Benchmark for Text Expansion: Datasets, Metrics, and Baselines

arXiv: https://arxiv.org/abs/2309.09198 · HTML: https://mlsanity.com/paper/2309.09198/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 53 references that are in the map.
- First posted on arXiv 17 Sep 2023.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [A Neural Attention Model for Abstractive Sentence Summarization](https://mlsanity.com/paper/1509.00685/) (2015)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [A Contrastive Framework for Neural Text Generation](https://mlsanity.com/paper/2202.06417/) (2022)
- [Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation](https://mlsanity.com/paper/1804.06609/) (2018)
- [GECToR -- Grammatical Error Correction: Tag, Not Rewrite](https://mlsanity.com/paper/2005.12592/) (2020)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [Insertion Transformer: Flexible Sequence Generation via Insertion Operations](https://mlsanity.com/paper/1902.03249/) (2019)
- [Training Neural Machine Translation To Apply Terminology Constraints](https://mlsanity.com/paper/1906.01105/) (2019)
- [Lexically Constrained Neural Machine Translation with Levenshtein Transformer](https://mlsanity.com/paper/2004.12681/) (2020)
- [Wordcraft: a Human-AI Collaborative Editor for Story Writing](https://mlsanity.com/paper/2107.07430/) (2021)
- [On the Evaluation Metrics for Paraphrase Generation](https://mlsanity.com/paper/2202.08479/) (2022)
- [Quality Controlled Paraphrase Generation](https://mlsanity.com/paper/2203.10940/) (2022)
- [Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora](https://mlsanity.com/paper/1806.03191/) (2018)
- [Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model](https://mlsanity.com/paper/2011.11499/) (2020)
- [Parallel Refinements for Lexically Constrained Text Generation with BART](https://mlsanity.com/paper/2109.12487/) (2021)
- [Writing Polishment with Simile: Task, Dataset and A Neural Approach](https://mlsanity.com/paper/2012.08117/) (2020)
- [Show Me How To Revise: Improving Lexically Constrained Sentence Generation with XLNet](https://mlsanity.com/paper/2109.05797/) (2021)
- [Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation](https://mlsanity.com/paper/2105.00666/) (2021)
- [A Question-answering Based Framework for Relation Extraction Validation](https://mlsanity.com/paper/2104.02934/) (2021)
- [InSRL: A Multi-view Learning Framework Fusing Multiple Information Sources for Distantly-supervised Relation Extraction](https://mlsanity.com/paper/2012.09370/) (2020)
- [Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction](https://mlsanity.com/paper/2105.05498/) (2021)
- [End-to-end Learning for Short Text Expansion](https://mlsanity.com/paper/1709.00389/) (2017)

## Abstract (arXiv)

This work presents a new task of Text Expansion (TE), which aims to insert fine-grained modifiers into proper locations of the plain text to concretize or vivify human writings. Different from existing insertion-based writing assistance tasks, TE requires the model to be more flexible in both locating and generation, and also more cautious in keeping basic semantics. We leverage four complementary approaches to construct a dataset with 12 million automatically generated instances and 2K human-annotated references for both English and Chinese. To facilitate automatic evaluation, we design various metrics from multiple perspectives. In particular, we propose Info-Gain to effectively measure the informativeness of expansions, which is an important quality dimension in TE. On top of a pre-trained text-infilling model, we build both pipelined and joint Locate&Infill models, which demonstrate the superiority over the Text2Text baselines, especially in expansion informativeness. Experiments verify the feasibility of the TE task and point out potential directions for future research toward better automatic text expansion.