Progressive Generation of Long Text with Pretrained Language Models
June 28, 2020 ยท Entered Twilight ยท ๐ arXiv.org
"Last commit was 5.0 years ago (โฅ5 year threshold)"
Evidence collected by the PWNC Scanner
Repo contents: LICENSE, README.md, bart_finetune.py, download, evaluate.py, generate.py, gpt2_finetune.py, make_stage.py, metrics, models, present_eval_results.py, scripts, train.py
Authors
Bowen Tan, Zichao Yang, Maruan AI-Shedivat, Eric P. Xing, Zhiting Hu
arXiv ID
2006.15720
Category
cs.CL: Computation & Language
Cross-listed
cs.LG
Citations
23
Venue
arXiv.org
Repository
https://github.com/tanyuqian/progressive-generation
โญ 82
Last Checked
1 month ago
Abstract
Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent long passages of text (e.g., 1000 tokens), especially when the models are fine-tuned to the target domain on a small corpus. Previous planning-then-generation methods also fall short of producing such long text in various domains. To overcome the limitations, we propose a simple but effective method of generating text in a progressive manner, inspired by generating images from low to high resolution. Our method first produces domain-specific content keywords and then progressively refines them into complete passages in multiple stages. The simple design allows our approach to take advantage of pretrained LMs at each stage and effectively adapt to any target domain given only a small set of examples. We conduct a comprehensive empirical study with a broad set of evaluation metrics, and show that our approach significantly improves upon the fine-tuned large LMs and various planning-then-generation methods in terms of quality and sample efficiency. Human evaluation also validates that our model generations are more coherent.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Computation & Language
๐
๐
Old Age
๐
๐
Old Age
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
R.I.P.
๐ป
Ghosted
Language Models are Few-Shot Learners
R.I.P.
๐ป
Ghosted
RoBERTa: A Robustly Optimized BERT Pretraining Approach
R.I.P.
๐ป
Ghosted
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
R.I.P.
๐ป
Ghosted