PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation
Open accessThe DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
Pre-trained Transformers have enabled impressive breakthroughs in generating long and fluent text, yet their outputs are often "rambling" without coherently arranged content.In this work, we present a novel content-controlled text generation framework, PAIR, with planning and iterative refinement, which is built upon a large model, BART.We first adapt the BERT model to automatically construct the content plans, consisting of keyphrase assignments and their corresponding sentence-level positions.The BART model is employed for generation without modifying its structure.We then propose a refinement algorithm to gradually enhance the generation quality within the sequence-tosequence framework.Evaluation with automatic metrics shows that adding planning consistently improves the generation quality on three distinct domains, with an average of 20 BLEU points and 12 METEOR points improvements.In addition, human judges rate our system outputs to be more relevant and coherent than comparisons without planning.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
The Curious Case of Neural Text Degeneration
Holtzman, A., Buys, J., Du, L., Forbes, M., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09751 · Cited by 1,304
Unified Language Model Pre-training for Natural Language Understanding and Generation
Dong, L., Yang, N., Wang, W., Wei, F., Liu, X., Wang, Y., Gao, J., Zhou, M., & Hon, H.-W. (2019) · arXiv · doi:10.48550/arxiv.1905.03197 · Cited by 1,225
The Penn Discourse TreeBank 2.0.
Prasad, R., Dinesh, N., Lee, A., Miltsakaki, E., Robaldo, L., Joshi, A., & Webber, B. (2008) · Proceedings of the Language Resources and Evaluation Conference · doi:10.63317/55sr8v9kexr7 · Cited by 1,115
Meteor: an automatic metric for MT evaluation with high levels of correlation with human judgments
Lavie, A., & Agarwal, A. (2007) · Proceedings of the Second Workshop on Statistical Machine Translation - StatMT '07 · doi:10.3115/1626355.1626389 · Cited by 1,047
CTRL: A Conditional Transformer Language Model for Controllable Generation
Keskar, N. S., McCann, B., Varshney, L. R., Xiong, C., & Socher, R. (2019) · arXiv · doi:10.48550/arxiv.1909.05858 · Cited by 751
Zhao, T., Zhao, R., & Eskenazi, M. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1061 · Cited by 736
Challenges in Data-to-Document Generation
Wiseman, S., Shieber, S., & Rush, A. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1239 · Cited by 524
Cited by
A Survey of Controllable Text Generation Using Transformer-based Pre-trained Language Models
Zhang, H., Song, H., Li, S., Zhou, M., & Song, D. (2024) · ACM Computing Surveys · doi:10.1145/3617680 · Cited by 317
Progressive Generation of Long Text with Pretrained Language Models
Tan, B., Yang, Z., Al-Shedivat, M., Xing, E., & Hu, Z. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.341 · Cited by 69
Nye, M., Tessler, M. H., Tenenbaum, J. B., & Lake, B. M. (2021) · arXiv · doi:10.48550/arxiv.2107.02794 · Cited by 40
Unmet Creativity Support Needs in Computationally Supported Creative Writing
Kreminski, M., & Martens, C. (2022) · Proceedings of the First Workshop on Intelligent and Interactive Writing Assistants (In2Writing 2022) · doi:10.18653/v1/2022.in2writing-1.11 · Cited by 26
Plot Writing From Pre-Trained Language Models
Jin, Y., Kadam, V., & Wanvarie, D. (2022) · arXiv · doi:10.48550/arxiv.2206.03021 · Cited by 1
Metadata
- Authors
- Hua, X., & Wang, L.
- Venue
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Published
- 2020
- Pages
- 781-793
- OpenAlex
- W3098295156
- Cited by
- 42
- References
- 18
- FWCI
- 3.33
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation. https://app.cochat.ai/papers/10.18653/v1/2020.emnlp-main.57
- The paper
- Hua, X., & Wang, L. (2020). PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). https://doi.org/10.18653/v1/2020.emnlp-main.57
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.