Ethan Lian

icon indicating a website link https://lianyixin.github.io/profile/

icon company MSDS @ Columbia University | BE @ SJTU icon location New York icon location NLP researcher | Business focused

Results 4 comments of Ethan Lian

I can't get the same results as the paper.

I got the same result with you, BLEU2: 0.9027 BLEU3: 0.7619 BLEU4: 0.5890 Hope the author can give us a clear explanation.

I can't get the same results as the paper.

Besides, it's worth pointing out that the bleu score in the adversarial training just bounces around the final value of pre-train stage, meaning that the adversarial training has no help...

I can't get the same results as the paper.

> Thanks for your remind, the decline of results may be caused by the update of NLTK [nltk/nltk#1844](https://github.com/nltk/nltk/pull/1844). The latest NLTK version updates the algorithm of BLEU, which may cause...

Embedding loss backwards?

original tf code is the same as in the paper: `e_latent_loss = tf.reduce_mean((tf.stop_gradient(quantized) - inputs) ** 2)` `q_latent_loss = tf.reduce_mean((quantized - tf.stop_gradient(inputs)) ** 2)` `loss = q_latent_loss + self._commitment_cost *...