Data-to-text Generation with Macro Planning
Open accessThe DOI matches its Crossref record; 73 of the 73 references it cites were found in a registry or an index.
Abstract
Recent approaches to data-to-text generation have adopted the very successful encoder-decoder architecture or variants thereof. These models generate text that is fluent (but often imprecise) and perform quite poorly at selecting appropriate content and ordering it coherently. To overcome some of these issues, we propose a neural model with a macro planning stage followed by a generation stage reminiscent of traditional methods which embrace separate modules for planning and surface realization. Macro plans represent high level organization of important content such as entities, events, and their interactions; they are learned from data and given as input to the generator. Extensive experiments on two data-to-text benchmarks (RotoWire and MLB) show that our approach outperforms competitive baselines in terms of automatic and human evaluation.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Planning can be a separate step in a two-step generator [32, 162, 208, 239, 269], which is prone to progressive amplification of the hallucination problem.”
From Survey of Hallucination in Natural Language Generation (2023) · cites this paper as [208]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Planning and skeleton generation are common methods to improve the faithfulness to the input in data-to-text tasks.”
From Survey of Hallucination in Natural Language Generation (2023) · cites this paper as [208]
Experimental — accuracy not yet measured
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Effective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382
(2010) · Cited by 8,261
Halliday, M. A. K., & Hasan, R. (2014) · Routledge eBooks · doi:10.4324/9781315836010 · Cited by 6,082
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al. (2016) · arXiv · doi:10.48550/arxiv.1609.08144 · Cited by 5,319 · cited 1×
“To reflect the fact that some records will be more important than others, we compute an attention weighted sum of {ei, j}|ei|j=1 following Yang et al. (2016).”
MethodHierarchical Attention Networks for Document Classification
Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., & Hovy, E. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1174 · Cited by 4,712
Research works printed but not linked: 3
- Louviere, 1991, Best-worst scaling: A model for the largest difference judgments, University of Alberta: Working Paper
- Orme, 2009, Maxdiff analysis: Simple counting, individual-level logit, and HB, Sawtooth Software
- Radford, 2019, Language models are unsupervised multitask learners, OpenAI blog, 1, 9
Cited by
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025
Gala, J. P., Chitale, P. A., Raghavan, A. K., Gumma, V., Doddapaneni, S., Kumar, A., Nawale, J. A., Sujatha, A., Puduppully, R., Raghavan, V., et al. (2023) · Transactions on machine learning research · doi:10.48550/arxiv.2305.16307 · Cited by 388
Self-citationAutomatic Generation of Socratic Subquestions for Teaching Math Word Problems
Shridhar, K., Mačina, J., El‐Assady, M., Sinha, T., Kapur, M., & Sachan, M. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.277 · Cited by 105
IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages
Kumar, A., Shrotriya, H., Sahu, P., Mishra, A., Dabre, R., Puduppully, R., Kunchukuttan, A., Khapra, M. M., & Kumar, P. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.360 · Cited by 82
Self-citationConditional Generation with a Question-Answering Blueprint
Narayan, S., Maynez, J., Amplayo, R. K., Ganchev, K., Louis, A. P., Huot, F., Sandholm, A., Das, D., & Lapata, M. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00583 · Cited by 67
Self-citation
Metadata
- Authors
- Puduppully, R., & Lapata, M.
- Affiliations
- University of Edinburgh (GB)
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press - Journals
- Published
- 2021
- Volume
- 9
- Pages
- 510-527
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W3128366560
- Semantic Scholar
- 1631a6e3b5235a4a2b0d71dca22a9614acca2ce3
- Cited by
- 53
- References
- 70
- Citations by year
- 2026: 6 · 2025: 7 · 2024: 7 · 2023: 17 · 2022: 15 · 2021: 1
- FWCI
- 3.54
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Transactions of the Association for Computational Linguistics (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, cc-by)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- data-to-text generation, macro planning, surface realization, content selection, coherence, encoder-decoder architecture, Major League Baseball
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: Data-to-text Generation with Macro Planning. https://app.cochat.ai/papers/10.1162/tacl_a_00381
- The paper
- Puduppully, R., & Lapata, M. (2021). Data-to-text Generation with Macro Planning. Transactions of the Association for Computational Linguistics. https://doi.org/10.1162/tacl_a_00381
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.