Friday, September 10, 2021

Seq2Seq Approaches in ML

 Seg2Seg


Seq2seq, developed by Google for use in machine translation, is a family of machine learning approaches used for language processing. Applications include language translation, image captioning, conversational models, and text summarization.


Source: https://towardsdatascience.com/understanding-encoder-decoder-sequence-to-sequence-model-679e04af4346


Seq2seq turns one sequence into another sequence (sequence transformation). It does so by use of a recurrent neural network (RNN) or more often LSTM or GRU to avoid the problem of vanishing gradient.

No comments:

Post a Comment

Why Write Tanka?

Why Write Tanka? By Janpha Thadphoothon I would like to introduce to you another poetic form from Japan – tanka. A tanka is a Japanese poem ...