You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Summary of "Conditional Generative Adversarial Nets" Paper
Conditional Generative Adversarial Nets
Introduction
Conditional version of Generative Adversarial Nets (GAN) where both generator and discriminator are conditioned on some data y (class label or data from some other modality).
Summary of "Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models" paper
Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models
Introduction
The paper presents a novel open vocabulary NMT(Neural Machine Translation) system that translates mostly at word level and falls back to character level models for rare words.
Advantages:
Faster and easier to train as compared to character models.
Does not produce unknown words in the translations which need to be removed using unk replacement techniques.