Bilingual-GAN: A Step Towards Parallel Text Generation

Ahmad Rashid, Alan Do-Omri, Md. Akmal Haidar, Qun Liu, Mehdi Rezagholizadeh


Abstract
Latent space based GAN methods and attention based sequence to sequence models have achieved impressive results in text generation and unsupervised machine translation respectively. Leveraging the two domains, we propose an adversarial latent space based model capable of generating parallel sentences in two languages concurrently and translating bidirectionally. The bilingual generation goal is achieved by sampling from the latent space that is shared between both languages. First two denoising autoencoders are trained, with shared encoders and back-translation to enforce a shared latent state between the two languages. The decoder is shared for the two translation directions. Next, a GAN is trained to generate synthetic ‘code’ mimicking the languages’ shared latent space. This code is then fed into the decoder to generate text in either language. We perform our experiments on Europarl and Multi30k datasets, on the English-French language pair, and document our performance using both supervised and unsupervised machine translation.
Anthology ID:
W19-2307
Volume:
Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Antoine Bosselut, Asli Celikyilmaz, Marjan Ghazvininejad, Srinivasan Iyer, Urvashi Khandelwal, Hannah Rashkin, Thomas Wolf
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
55–64
Language:
URL:
https://aclanthology.org/W19-2307
DOI:
10.18653/v1/W19-2307
Bibkey:
Cite (ACL):
Ahmad Rashid, Alan Do-Omri, Md. Akmal Haidar, Qun Liu, and Mehdi Rezagholizadeh. 2019. Bilingual-GAN: A Step Towards Parallel Text Generation. In Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation, pages 55–64, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Bilingual-GAN: A Step Towards Parallel Text Generation (Rashid et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-2307.pdf