MaskGAN: Better Text Generation via Filling in the _______
Authors: William Fedus, Ian Goodfellow, Andrew M. Dai
ICLR 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We present both conditional and unconditional samples generated on the PTB and IMDB data sets at word-level. We produce samples conditioned on surrounding text in Table 1. The Mechanical Turk results show that Mask GAN generates superior human-looking samples to Mask MLE on the IMDB dataset. |
| Researcher Affiliation | Industry | William Fedus, Ian Goodfellow and Andrew M. Dai Google Brain liam.fedus@gmail.com, {goodfellow, adai}@google.com |
| Pseudocode | No | No pseudocode or algorithm blocks are explicitly provided in the paper. |
| Open Source Code | Yes | Mask GAN source code available at: https://github.com/tensorflow/models/tree/ master/research/maskgan |
| Open Datasets | Yes | The Penn Treebank dataset (Marcus et al., 1993) has a vocabulary of 10,000 unique words. The IMDB dataset Maas et al. (2011) consists of 100,000 movie reviews taken from IMDB. |
| Dataset Splits | Yes | The training set contains 930,000 words, the validation set contains 74,000 words and the test set contains 82,000 words. |
| Hardware Specification | No | No specific hardware details (e.g., GPU/CPU models, memory) are mentioned for running the experiments. |
| Software Dependencies | No | The paper mentions 'TensorFlow' but does not provide a specific version number for it or other software dependencies. |
| Experiment Setup | Yes | Our model uses 2-layers of 650 unit LSTMs for both the generator and discriminator, 650 dimensional word embeddings, variational dropout. We used Bayesian hyperparameter tuning to tune the variational dropout rate and learning rates for the generator, discriminator and critic. We perform 3 gradient descent steps on the discriminator for every step on the generator and critic. |