Generative Adversarial Networks for Text Using Word2vec Intermediaries
Akshay Budhkar, Krishnapriya Vishnubhotla, Safwan Hossain, Frank Rudzicz
Abstract
Generative adversarial networks (GANs) have shown considerable success, especially in the realistic generation of images. In this work, we apply similar techniques for the generation of text. We propose a novel approach to handle the discrete nature of text, during training, using word embeddings. Our method is agnostic to vocabulary size and achieves competitive results relative to methods with various discrete gradient estimators.- Anthology ID:
- W19-4303
- Volume:
- Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Isabelle Augenstein, Spandana Gella, Sebastian Ruder, Katharina Kann, Burcu Can, Johannes Welbl, Alexis Conneau, Xiang Ren, Marek Rei
- Venue:
- RepL4NLP
- SIG:
- SIGREP
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 15–26
- Language:
- URL:
- https://aclanthology.org/W19-4303
- DOI:
- 10.18653/v1/W19-4303
- Cite (ACL):
- Akshay Budhkar, Krishnapriya Vishnubhotla, Safwan Hossain, and Frank Rudzicz. 2019. Generative Adversarial Networks for Text Using Word2vec Intermediaries. In Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), pages 15–26, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Generative Adversarial Networks for Text Using Word2vec Intermediaries (Budhkar et al., RepL4NLP 2019)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/W19-4303.pdf