mlsanityData to 14 Oct 2026

AGGGEN: Ordering and Aggregating while Generating

arXiv 2106.05580 ↗First posted 10 Jun 2021cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

We present AGGGEN (pronounced 'again'), a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. In contrast to previous work using sentence planning, our model is still end-to-end: AGGGEN performs sentence planning at the same time as generating text by learning latent alignments (via semantic facts) between input representation and target text. Experiments on the WebNLG and E2E challenge data show that by using fact-based alignments our approach is more interpretable, expressive, robust to noise, and easier to control, while retaining the advantages of end-to-end systems in terms of fluency. Our code is available at https://github.com/XinnuoXu/AggGen.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 33 of its 55 references that are in the map. First posted on arXiv 10 Jun 2021.

Builds on

33 of 55 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,046
  5. 2018Object Hallucination in Image Captioningcited by 669
  6. 2017The E2E Dataset: New Challenges For End-to-End Generationcited by 253
  7. 2017Challenges in Data-to-Document Generationcited by 226
  8. 2017Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluationcited by 206
  9. 2017Faithful to the Original: Fact Aware Neural Abstractive Summarizationcited by 141
  10. 2015Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systemscited by 134
  11. 2019Strategies for Structuring Story Generationcited by 124
  12. 2018Data-to-Text Generation with Content Selection and Planningcited by 106
21 more
  1. 2020Text-to-Text Pre-Training for Data-to-Text Taskscited by 104
  2. 2019Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challengecited by 86
  3. 2019Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generationcited by 75
  4. 2019Barack's Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modelingcited by 71
  5. 2019Semantic Noise Matters for Neural Natural Language Generationcited by 64
  6. 2019Long and Diverse Text Generation with Planning-based Hierarchical Variational Modelcited by 62
  7. 2018Learning Neural Templates for Text Generationcited by 61
  8. 2019Neural data-to-text generation: A comparison between pipeline and end-to-end architecturescited by 51
  9. 2018Jointly Predicting Predicates and Arguments in Neural Semantic Role Labelingcited by 34
  10. 2016Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Stringscited by 27
  11. 2018Deep Graph Convolutional Encoders for Structured Data to Text Generationcited by 27
  12. 2020Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondencecited by 25
  13. 2018A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generationcited by 20
  14. 2015Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Rerankingcited by 17
  15. 2019A Good Sample is Hard to Find: Noise Injection Sampling and Self-Training for Neural Language Generation Modelscited by 17
  16. 2020Posterior Control of Blackbox Generationcited by 16
  17. 2018Can Neural Generators for Dialogue Learn Sentence Planning and Discourse Structuring?cited by 12
  18. 2018Natural Language Generation by Hierarchical Decoding with Linguistic Patternscited by 11
  19. 2019Semi-Supervised Neural Text Generation by Joint Learning of Natural Language Generation and Natural Language Understanding Modelscited by 9
  20. 2019Improving Quality and Efficiency in Plan-based Neural Data-to-Text Generationcited by 7
  21. 2019Designing a Symbolic Intermediate Representation for Neural Surface Realizationcited by 4

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 2; 2024: 1.

7 papers.

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  2. 2022Conditional Generation with a Question-Answering Blueprintcited by 44
  3. 2022Neural Pipeline for Zero-Shot Data-to-Text Generationcited by 19
  4. 2022Recent Advances in Neural Text Generation: A Task-Agnostic Surveycited by 14
  5. 2023Generating Faithful Text From a Knowledge Graph with Noisy Reference Textcited by 4
  6. 2024A Systematic Review of Data-to-Text NLGcited by 4
  7. 2023You Can Generate It Again: Data-to-Text Generation with Verification and Correction Promptingcited by 2