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
Natural language processing with Python
Bird, S., Klein, E., & Loper, E. (2009) · CERN Document Server (European Organization for Nuclear Research) · Cited by 3,955
Bleu: a method for automatic evaluation of machine translation
Papineni, K. (2024) · doi:10.57702/ljteqmrb · Cited by 3,672
Vinyals, O., Fortunato, M., & Jaitly, N. (2015) · neural information processing systems · Cited by 2,043
OpenNMT: Open-Source Toolkit for Neural Machine Translation
Klein, G., Kim, Y., Deng, Y., Senellart, J., & Rush, A. (2017) · Proceedings of ACL 2017, System Demonstrations · doi:10.18653/v1/p17-4012 · Cited by 1,749
Incorporating Copying Mechanism in Sequence-to-Sequence Learning
Gu, J., Lu, Z., Li, H., & Li, V. O. K. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1154 · Cited by 1,446
Building Natural-Language Generation Systems
Reiter, E. (1996) · arXiv (Cornell University) · doi:10.48550/arxiv.cmp-lg/9605002 · Cited by 1,228
A Deep Reinforced Model for Abstractive Summarization
Paulus, R., Xiong, C., & Socher, R. (2017) · arXiv · doi:10.48550/arxiv.1705.04304 · Cited by 1,182
Neural Machine Translation of Rare Words with Subword Units
Sennrich, R., Haddow, B., & Birch, A. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1162 · Cited by 974
Neural Machine Translation of Rare Words with Subword Units
Sennrich, R., Haddow, B., & Birch, A. (2015) · arXiv · doi:10.48550/arxiv.1508.07909 · Cited by 950
Gatt, A., & Krahmer, E. (2018) · Journal of Artificial Intelligence Research · doi:10.1613/jair.5477 · Cited by 776
Building Natural Language Generation Systems
Reiter, E., & Dale, R. (2000) · Cambridge University Press eBooks · doi:10.1017/cbo9780511519857 · Cited by 772
McKeown, K. (1985) · Cambridge University Press eBooks · doi:10.1017/cbo9780511620751 · Cited by 757
Building applied natural language generation systems
REITER, E., & DALE, R. (1997) · Natural Language Engineering · doi:10.1017/s1351324997001502 · Cited by 631
Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting
Chen, Y.-C., & Bansal, M. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1063 · Cited by 595
An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories
Williams, R. J., & Peng, J. (1990) · Neural Computation · doi:10.1162/neco.1990.2.4.490 · Cited by 577
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
Best-Worst Scaling: Theory, Methods and Applications
Louviere, J. J., Flynn, T. N., & Marley, A. A. J. (2015) · Cambridge University Press eBooks · doi:10.1017/cbo9781107337855 · Cited by 522
Gulcehre, C., Ahn, S., Nallapati, R., Zhou, B., & Bengio, Y. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1014 · Cited by 478
Neural Text Generation from Structured Data with Application to the Biography Domain
Lebret, R., Grangier, D., & Auli, M. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1128 · Cited by 444
(2017) · doi:10.18653/v1/p17-1017 · Cited by 436
Best-Worst Scaling: Theory, Methods and Applications
Louviere, J. J., Flynn, T. N., & Marley, A. A. J. (2015) · Thammasat University Digital Collections · Cited by 435
Automated discourse generation using discourse structure relations
Hovy, E. H. (1993) · Artificial Intelligence · doi:10.1016/0004-3702(93)90021-3 · Cited by 303
Controllable Abstractive Summarization
Fan, A., Grangier, D., & Auli, M. (2018) · Proceedings of the 2nd Workshop on Neural Machine Translation and Generation · doi:10.18653/v1/w18-2706 · Cited by 281 · cited 1×
“Ideas such as length normalisation (Wu et al., 2016) or length control (Kikuchi et al., 2016; Takeno et al., 2017; Fan et al., 2018) could help alleviate this; however, we do not pursue them further for fair comparison with the other models.”
ResultIncorporating Copying Mechanism in Sequence-to-Sequence LearningPreprint
Gu, J., Lu, Z., Li, H., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.06393 · Cited by 258
What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment
Mei, H., Bansal, M., & Walter, M. R. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1086 · Cited by 237
Do NLP Models Know Numbers? Probing Numeracy in Embeddings
Wallace, E., Wang, Y., Li, S., Singh, S., & Gardner, M. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1534 · Cited by 227
Controlling Output Length in Neural Encoder-Decoders
Kikuchi, Y., Neubig, G., Sasano, R., Takamura, H., & Okumura, M. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1140 · Cited by 222
The E2E Dataset: New Challenges For End-to-End Generation
Novikova, J., Dušek, O., & Rieser, V. (2017) · Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue · doi:10.18653/v1/w17-5525 · Cited by 220
The Flow of Thought and the Flow of Language
Chafe, W. L. (1979) · Discourse and Syntax · doi:10.1163/9789004368897_008 · Cited by 217
Best practices for the human evaluation of automatically generated text
van der Lee, C., Gatt, A., van Miltenburg, E., Wubben, S., & Krahmer, E. (2019) · Proceedings of the 12th International Conference on Natural Language Generation · doi:10.18653/v1/w19-8643 · Cited by 205 · cited 3×
“They exper-iment with the WebNLG dataset (Gardent et al., 2017) which consists of RDF Subject, Object, Predicate triples paired with corresponding text.”
MethodDesign of a knowledge-based report generator
Kukich, K. (1983) · Proceedings of the 21st annual meeting on Association for Computational Linguistics - · doi:10.3115/981311.981340 · Cited by 202
Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation
Moryossef, A., Goldberg, Y., & Dagan, I. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-1236 · Cited by 202
Collective content selection for concept-to-text generation
Barzilay, R., & Lapata, M. (2005) · Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing - HLT '05 · doi:10.3115/1220575.1220617 · Cited by 185
Self-citationThe Paragraph as a Grammatical Unit
Longacre, R. E. (1979) · Discourse and Syntax · doi:10.1163/9789004368897_006 · Cited by 169
Integrating Selectional Constraints and Subcategorization Frames in a Dependency Parser
(2016) · HAL · doi:10.1162/coli · Cited by 135
NLG vs. TemplatesPreprint
Reiter, E. (1995) · arXiv (Cornell University) · doi:10.48550/arxiv.cmp-lg/9504013 · Cited by 135
Data-to-text Generation with Entity Modeling
Puduppully, R., Dong, L., & Lapata, M. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1195 · Cited by 113
Self-citationNeural data-to-text generation: A comparison between pipeline and end-to-end architectures
Ferreira, T. C., van der Lee, C., van Miltenburg, E., & Krahmer, E. (2019) · Tilburg University Research Portal · Cited by 110
Long and Diverse Text Generation with Planning-based Hierarchical Variational Model
Shao, Z., Huang, M., Wen, J., Xu, W., & Zhu, X. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1321 · Cited by 91
A Hierarchical Model for Data-to-Text Generation
Rebuffel, C., Soulier, L., Scoutheeten, G., & Gallinari, P. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-45439-5_5 · Cited by 69
Generating referring expressions in a domain of objects and processes
Dale, R. (1989) · OpenGrey (Institut de l'Information Scientifique et Technique) · Cited by 62
MasakhaNER: Named entity recognition for African languages
(2021) · HAL · doi:10.1162/tacl · Cited by 61
Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation
Tian, R., Narayan, S., Sellam, T., & Parikh, A. P. (2019) · arXiv · doi:10.48550/arxiv.1910.08684 · Cited by 60 · cited 1×
“…are represented (Puduppully et al., 2019b; Iso et al., 2019), allowing the decoder to skip low-confidence to-kens to enhance faithful generation (Tian et al., 2019), and making the encoder-decoder architecture more modular by introducing micro planning (Puduppully et al., 2019a; Moryossef et…”
Zadrozny, W., & Jensen, K. (1991) · OLAC - Open Language Archives Community · doi:10.5555/971750.971753 · Cited by 59
Gong, H., Feng, X., Qin, B., & Liu, T. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1310 · Cited by 53
Inducing Document Plans for Concept-to-Text Generation
Konstas, I., & Lapata, M. (2013) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d13-1157 · Cited by 52
Self-citationEmpirically estimating order constraints for content planning in generation
Duboue, P. A., & McKeown, K. R. (2001) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.3115/1073012.1073035 · Cited by 51
Simple and Effective Noisy Channel Modeling for Neural Machine Translation
Yee, K., Dauphin, Y., & Auli, M. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1571 · Cited by 49
Language generation for multimedia healthcare briefings
McKeown, K. R., Pan, S., Shaw, J., Jordan, D. A., & Allen, B. A. (1997) · Proceedings of the fifth conference on Applied natural language processing - · doi:10.3115/974557.974598 · Cited by 47
Bootstrapping Generators from Noisy Data
Perez-Beltrachini, L., & Lapata, M. (2018) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n18-1137 · Cited by 47
Self-citationOperation-guided Neural Networks for High Fidelity Data-To-Text Generation
Nie, F., Wang, J., Yao, J.-G., Pan, R., & Lin, C.-Y. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1422 · Cited by 46
Learning to Select, Track, and Generate for Data-to-Text
Iso, H., Uehara, Y., Ishigaki, T., Noji, H., Aramaki, E., Kobayashi, I., Miyao, Y., Okazaki, N., & Takamura, H. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1202 · Cited by 45
Better Document-Level Machine Translation with Bayes’ Rule
Yu, L., Sartran, L., Stokowiec, W., Ling, W., Kong, L., Blunsom, P., & Dyer, C. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00319 · Cited by 41
Content planner construction via evolutionary algorithms and a corpus-based fitness function
McKeown, K. R., & Duboue, P. A. (2002) · doi:10.7916/d83t9rjx · Cited by 38
(2019) · doi:10.1609/aaai.v33i01.33016908 · Cited by 26
Self-citationCorpus-Trained Text Generation for Summarization
Kan, M., & McKeown, K. R. (2002) · doi:10.7916/d88p67w7 · Cited by 23
Investigating content selection for language generation using machine learning
Kelly, C., Copestake, A., & Karamanis, N. (2009) · doi:10.3115/1610195.1610218 · Cited by 18
Controlling Target Features in Neural Machine Translation via Prefix Constraints
Takeno, S., Nagata, M., & Yamamoto, K. (2017) · Cited by 18
Scalable Micro-planned Generation of Discourse from Structured Data
Laha, A., Jain, P., Mishra, A., & Sankaranarayanan, K. (2019) · Computational Linguistics · doi:10.1162/coli_a_00363 · Cited by 14
Naver Labs Europe’s Systems for the Document-Level Generation and Translation Task at WNGT 2019
Saleh, F., Berard, A., Calapodescu, I., & Besacier, L. (2019) · Workshop on Neural Generation and Translation (WNGT) · doi:10.18653/v1/d19-5631 · Cited by 13
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
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.