CoChat

A survey on text generation using generative adversarial networks

Open access
de Rosa, Gustavo H., Papa, João P. · 2021 · Pattern Recognition
Cited by 129

The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.

Abstract

This work presents a thorough review concerning recent studies and text generation advancements using Generative Adversarial Networks. The usage of adversarial learning for text generation is promising as it provides alternatives to generate the so-called “natural” language. Nevertheless, adversarial text generation is not a simple task as its foremost architecture, the Generative Adversarial Networks, were designed to cope with continuous information (image) instead of discrete data (text). Thus, most works are based on three possible options, i.e., Gumbel-Softmax differentiation, Reinforcement Learning, and modified training objectives. All alternatives are reviewed in this survey as they present the most recent approaches for generating text using adversarial-based techniques. The selected works were taken from renowned databases, such as Science Direct, IEEEXplore, Springer, Association for Computing Machinery, and arXiv, whereas each selected work has been critically analyzed and assessed to present its objective, methodology, and experimental results.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.patcog.2021.108098

Cites

11 of 11 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 11 references

Research works printed but not linked: 34

  1. Zhang, 2021, A survey on concept factorization: from shallow to deep representation learning, Inf. Process. Manage., 58, 102534, 10.1016/j.ipm.2021.102534 · DOI
  2. Zhang, 2021, Dense residual network: enhancing global dense feature flow for character recognition, Neural Netw., 139, 77, 10.1016/j.neunet.2021.02.005 · DOI
  3. Elman, 1990, Finding structure in time, Cognit. Sci., 14, 179, 10.1207/s15516709cog1402_1 · DOI · Paper page
  4. Biggio, 2018, Wild patterns: ten years after the rise of adversarial machine learning, Pattern Recognit., 84, 317, 10.1016/j.patcog.2018.07.023 · DOI · Paper page
  5. Hu, 2019, Face hallucination from low quality images using definition-scalable inference, Pattern Recognit., 94, 110, 10.1016/j.patcog.2019.05.027 · DOI
  6. Li, 2020, Semi-supervised cross-modal image generation with generative adversarial networks, Pattern Recognit., 100, 107085, 10.1016/j.patcog.2019.107085 · DOI
  7. Liu, 2020, Collocating clothes with generative adversarial networks cosupervised by categories and attributes: a multidiscriminator framework, IEEE Trans. Neural Netw. Learn.Syst., 31, 3540, 10.1109/TNNLS.2019.2944979 · DOI
  8. Sutton, 1998, vol. 135
  9. T. Che, Y. Li, R. Zhang, R.D. Hjelm, W. Li, Y. Song, Y. Bengio, Maximum-likelihood augmented discrete generative adversarial networks, 2017, arXiv preprint arXiv:1702.07983 · arXiv
  10. S. Lu, Y. Zhu, W. Zhang, J. Wang, Y. Yu, Neural text generation: past, present and beyond, 2018, arXiv preprint arXiv:1803.07133 · arXiv
  11. Zhang, 2020, Adversarial attacks on deep-learning models in natural language processing: a survey, ACM Trans. Intell. Syst.Technol., 11, 1
  12. Goldberg, 2016, A primer on neural network models for natural language processing, J. Artif. Intell. Res., 57, 345, 10.1613/jair.4992 · DOI · Paper page
  13. Williams, 1992, Simple statistical gradient-following algorithms for connectionist reinforcement learning, Mach. Learn., 8, 229, 10.1007/BF00992696 · DOI · Paper page
  14. Ondrej, 2017, Findings of the 2017 conference on machine translation (WMT17), 169
  15. Brown, 1992, An estimate of an upper bound for the entropy of english, Comput. Linguist., 18, 31
  16. M.J. Kusner, J.M. Hernández-Lobato, GANs for sequences of discrete elements with the Gumbel-Softmax distribution, 2016, arXiv preprint arXiv:1611.04051 · arXiv
  17. G.L. Guimaraes, B. Sanchez-Lengeling, C. Outeiral, P.L.C. Farias, A. Aspuru-Guzik, Objective-reinforced generative adversarial networks (organ) for sequence generation models, 2018, arXiv preprint arXiv:1705.10843 · arXiv
  18. Li, 2018, A generative model for category text generation, Inf. Sci., 450, 301, 10.1016/j.ins.2018.03.050 · DOI · Paper page
  19. A. Balagopalan, S. Gorti, M. Ravaut, R. Saqur, ReGAN: RE[LAX|BAR|INFORCE] based sequence generation using GANs, 2018, arXiv preprint arXiv:1805.02788 · arXiv
  20. Chen, 2020, Customizable text generation via conditional text generative adversarial network, Neurocomputing, 416, 125, 10.1016/j.neucom.2018.12.092 · DOI
  21. Wang, 2019, Automatic generation of sentimental texts via mixture adversarial networks, Artif. Intell., 275, 540, 10.1016/j.artint.2019.07.003 · DOI
  22. Zhang, 2019, Emotional text generation based on cross-domain sentiment transfer, IEEE Access, 7, 100081, 10.1109/ACCESS.2019.2931036 · DOI
  23. Liu, 2019, BFGAN: backward and forward generative adversarial networks for lexically constrained sentence generation, IEEE/ACM Trans. Audio Speech Lang. Process., 27, 2350, 10.1109/TASLP.2019.2943018 · DOI
  24. Sun, 2019, QuGAN: quasi generative adversarial network for tibetan question answering corpus generation, IEEE Access, 7, 116247, 10.1109/ACCESS.2019.2934581 · DOI
  25. Rizzo, 2020, Adversarial text generation with context adapted global knowledge and a self-attentive discriminator, Inf. Process. Manage., 57, 102217, 10.1016/j.ipm.2020.102217 · DOI
  26. Wu, 2020, Text generation service model based on truth-guided seqGAN, IEEE Access, 8, 11880, 10.1109/ACCESS.2020.2966291 · DOI
  27. W. Zhou, T. Ge, K. Xu, F. Wei, M. Zhou, Self-adversarial learning with comparative discrimination for text generation, 2020, arXiv preprint arXiv:2001.11691 · arXiv
  28. O. Press, A. Bar, B. Bogin, J. Berant, L. Wolf, Language generation with recurrent generative adversarial networks without pre-training, 2017, arXiv preprint arXiv:1706.01399 · arXiv
  29. D. Donahue, A. Rumshisky, Adversarial text generation without reinforcement learning, 2018, arXiv preprint arXiv:1810.06640 · arXiv
  30. Montahaei, 2021, DGSAN: discrete generative self-adversarial network, Neurocomputing, 448, 364, 10.1016/j.neucom.2021.03.097 · DOI
  31. Yang, 2020, FGGAN: feature-guiding generative adversarial networks for text generation, IEEE Access, 8, 105217, 10.1109/ACCESS.2020.2993928 · DOI
  32. Ziebart, 2008, Maximum entropy inverse reinforcement learning., vol. 3, 1433
  33. Zhang, 2016, Generating text via adversarial training, vol. 21
  34. Radford, 2019, Language models are unsupervised multitask learners, OpenAI Blog, 1, 1

Cited by

See all 129

Metadata

Authors
de Rosa, G. H., & Papa, J. P.
Venue
Pattern Recognition
Publisher
Elsevier BV
Published
2021-11
Volume
119
Pages
108098
ISSN
0031-3203 (ISSN-L)
OpenAlex
W3165906701
Cited by
129
References
11
FWCI
7.32
Type
journal article
Language
en
Open access
green
Funders
  • National Council for Forest Research and Development
  • Fundação de Amparo à Pesquisa do Estado de São Paulo (2013/07375-0, 2014/12236-1, 2019/02205-5, 2019/07665-4, 2020/12101-0)
  • Conselho Nacional de Desenvolvimento Científico e Tecnológico (307066/2017-7, 427968/2018-6)

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: A survey on text generation using generative adversarial networks. https://app.cochat.ai/papers/10.1016/j.patcog.2021.108098
The paper
de Rosa, G. H., & Papa, J. P. (2021). A survey on text generation using generative adversarial networks. Pattern Recognition. https://doi.org/10.1016/j.patcog.2021.108098

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.