Adversarial Generation of Natural Language
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Generative Adversarial Networks (GANs) have gathered a lot of attention from the computer vision community, yielding impressive results for image generation.Advances in the adversarial generation of natural language from noise however are not commensurate with the progress made in generating images, and still lag far behind likelihood based methods.In this paper, we take a step towards generating natural language with a GAN objective alone.We introduce a simple baseline that addresses the discrete output space problem without relying on gradient estimators and show that it is able to achieve state-of-the-art results on a Chinese poem generation dataset.We present quantitative results on generating sentences from context-free and probabilistic context-free grammars, and qualitative language modeling results.A conditional version is also described that can generate sequences conditioned on sentence characteristics.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545
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
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235
Conditional Generative Adversarial Nets
Mirza, M., & Osindero, S. (2014) · arXiv · doi:10.48550/arxiv.1411.1784 · Cited by 8,863
Building a Large Annotated Corpus of English: The Penn Treebank
Marcus, M. (1993) · doi:10.21236/ada273556 · Cited by 7,405
Improved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965
Improved training of Wasserstein GANs
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. (2017) · arXiv · doi:10.48550/arxiv.1704.00028 · Cited by 6,800 · cited 12×
“2 shows the negative-log-likelihood of generated samples using a LSTM architecture using the WGAN-GP, GAN-GP and MLE criteria.”
BackgroundMethodInfluentialSelf-citation“Least squares generative adversarial networks,”
Mao, X., Li, Q., Xie, H., Lau, R. Y. K., Wang, Z., & Smolley, S. P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.304 · Cited by 5,437
Recurrent neural network based language model
Mikolov, T., Karafiát, M., Burget, L., Černocký, J., & Khudanpur, S. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-343 · Cited by 5,390 · cited 2×
“Recurrent Neural Networks (RNNs), particularly Long short-term memory networks (LSTMs) (Hochreiter and Schmidhuber, 1997) and Gated Recurrent Networks (Cho et al., 2014) are powerful models that have been successful at modeling sequential data (Graves and Schmidhuber, 2009; Mikolov et al., 2010).”
BackgroundBengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“As a way to provide training signals of incremental difficulty, we use curriculum learning (Bengio et al., 2009) and train our generator to produce sequences of gradually increasing lengths as training progresses.”
MethodA Learning Algorithm for Continually Running Fully Recurrent Neural Networks
Williams, R. J., & Zipser, D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.2.270 · Cited by 4,369 · cited 1×
“These models are commonly trained using a technique called teacher forcing (Williams and Zipser, 1989) where the inputs to the network are fixed and the model is trained to predict only the next ∗ Indicates first authors.”
MethodCategorical Reparameterization with Gumbel-Softmax
Jang, E., Gu, S., & Poole, B. (2016) · arXiv · doi:10.48550/arxiv.1611.01144 · Cited by 3,616
Arjovsky, M., Chintala, S., & Bottou, L. (2017) · arXiv · doi:10.48550/arxiv.1701.07875 · Cited by 2,225
Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
Bengio, Y., Léonard, N., & Courville, A. (2013) · arXiv · doi:10.48550/arxiv.1308.3432 · Cited by 1,910 · cited 1×
“Other alternatives include RE-INFORCE (Williams, 1992), the use of a Gumbel softmax (Jang et al., 2016) and the straighthrough estimator (Bengio et al., 2013) among others.”
MethodSelf-citationScheduled Sampling for Sequence Prediction with Recurrent Neural Networks
Bengio, S., Vinyals, O., Jaitly, N., & Shazeer, N. (2015) · arXiv · doi:10.48550/arxiv.1506.03099 · Cited by 1,621 · cited 1×
“However this one-step ahead prediction during training makes the model prone to exposure bias (Ranzato et al., 2015; Bengio et al., 2015).”
BackgroundCharacter-Aware Neural Language Models
Kim, Y., Jernite, Y., Sontag, D., & Rush, A. M. (2015) · arXiv · doi:10.48550/arxiv.1508.06615 · Cited by 1,530
Sequence Level Training with Recurrent Neural Networks
Ranzato, M., Chopra, S., Auli, M., & Zaremba, W. (2015) · arXiv · doi:10.48550/arxiv.1511.06732 · Cited by 1,426 · cited 1×
“However this one-step ahead prediction during training makes the model prone to exposure bias (Ranzato et al., 2015; Ben-gio et al., 2015).”
Backgroundf-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
Nowozin, S., Cseke, B., & Tomioka, R. (2016) · arXiv · doi:10.48550/arxiv.1606.00709 · Cited by 1,183 · cited 1×
“Nowozin et al. (2016) show that it is possible to train GANs with a variety of f-divergence measures besides JSD. Wasserstein GANs (WGANs) (Arjovsky et al., 2017) minimize the earth mover’s distance or Wasserstein distance, while Least Squared GANs (LSGANs) (Mao et al., 2016) modifies replaces the…”
BackgroundOne Billion Word Benchmark for Measuring Progress in Statistical Language Modeling
Chelba, C., Mikolov, T., Schuster, M., Ge, Q., Brants, T., Koehn, P., & Robinson, T. (2013) · arXiv · doi:10.48550/arxiv.1312.3005 · Cited by 1,051
Simple statistical gradient-following algorithms for connectionist reinforcement learning
Williams, R. J. (1992) · Machine Learning · doi:10.1023/a:1022672621406 · Cited by 817
One billion word benchmark for measuring progress in statistical language modeling
Chelba, C., Mikolov, T., Schuster, M., Ge, Q., Brants, T., Koehn, P., & Robinson, T. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-564 · Cited by 627 · cited 1×
“A dataset comprising simple English sentences 3 which we will henceforth refer to as CMU − SE, the version of the Penn Treebank commonly used in language modeling experiments (Zaremba et al., 2014) and the Google 1-billion word dataset (Chelba et al., 2013).”
MethodOn the quantitative analysis of deep belief networks
Salakhutdinov, R., & Murray, I. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390266 · Cited by 411 · cited 1×
“Figure 3 shows samples generated on the binarized MNIST dataset (Salakhutdinov and Murray, 2008).”
BackgroundChinese Poetry Generation with Recurrent Neural Networks
Zhang, X., & Lapata, M. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1074 · Cited by 298 · cited 1×
“Zhang and Lapata (2014) present a dataset of Chinese poems that were used to evaluate adversarial training methods for natural language in (Yu et al., 2016) and (Che et al., 2017).”
Background
Cited by
Recent Trends in Deep Learning Based Natural Language Processing [Review Article]
Young, T., Hazarika, D., Poria, S., & Cambria, E. (2018) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2018.2840738 · Cited by 2,921
Deep Neural Networks and Tabular Data: A Survey
Borisov, V., Leemann, T., Seßler, K., Haug, J., Pawelczyk, M., & Kasneci, G. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3229161 · Cited by 1,025
Long Text Generation via Adversarial Training with Leaked Information
Guo, J., Lu, S., Cai, H., Zhang, W., Yu, Y., & Wang, J. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11957 · Cited by 499
Soviany, P., Ionescu, R. T., Rota, P., & Sebe, N. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01611-x · Cited by 431
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
“This is exemplified by work focusing on natural language generation such as (Bowman et al., 2016; Yu et al., 2017; Zhao et al., 2017; Rajeswar et al., 2017).”
Background
Metadata
- Authors
- Subramanian, S., Rajeswar, S., Dutil, F., Pal, C., & Courville, A.
- Venue
- Proceedings of the 2nd Workshop on Representation Learning for NLP
- Published
- 2017
- Pages
- 241-251
- OpenAlex
- W2964028737
- Cited by
- 112
- References
- 26
- FWCI
- 4.93
- 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
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.