stat946w18/Unsupervised Machine Translation Using Monolingual Corpora Only: Difference between revisions
Jump to navigation
Jump to search
(Created page with "File:Under-Construction-Sign.gif == Introduction == Neural Machine translation systems must be trained on large corpora consisting of pairs of pre-translated sentences. T...") |
|||
Line 2: | Line 2: | ||
== Introduction == | == Introduction == | ||
Neural | Neural machine translation systems must be trained on large corpora consisting of pairs of pre-translated sentences. This paper proposes an unsupervised neural machine translation system, which can be trained without using any such parallel data. | ||
== Overview of Translation System == | == Overview of Translation System == |
Revision as of 19:40, 17 February 2018
Introduction
Neural machine translation systems must be trained on large corpora consisting of pairs of pre-translated sentences. This paper proposes an unsupervised neural machine translation system, which can be trained without using any such parallel data.
Overview of Translation System
The unsupervised translation system has four components:
- An unsupervised word-vector alignment system
- An encoder
- A decoder
- A discriminator
Overview of Objective
The objective function is the sum of three terms:
- The de-noising auto-encoder loss
- The translation loss
- The adversarial loss