Word Representation Models for Morphologically Rich Languages in Neural Machine Translation

06/14/2016
by   Ekaterina Vylomova, et al.
0

Dealing with the complex word forms in morphologically rich languages is an open problem in language processing, and is particularly important in translation. In contrast to most modern neural systems of translation, which discard the identity for rare words, in this paper we propose several architectures for learning word representations from character and morpheme level word decompositions. We incorporate these representations in a novel machine translation model which jointly learns word alignments and translations via a hard attention mechanism. Evaluating on translating from several morphologically rich languages into English, we show consistent improvements over strong baseline methods, of between 1 and 1.5 BLEU points.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/07/2016

Improving the Performance of Neural Machine Translation Involving Morphologically Rich Languages

The advent of the attention mechanism in neural machine translation mode...
research
03/02/2016

Character-based Neural Machine Translation

Neural Machine Translation (MT) has reached state-of-the-art results. Ho...
research
12/12/2019

Two Way Adversarial Unsupervised Word Translation

Word translation is a problem in machine translation that seeks to build...
research
08/18/2015

Probabilistic Modelling of Morphologically Rich Languages

This thesis investigates how the sub-structure of words can be accounted...
research
11/19/2019

A Hybrid Morpheme-Word Representation for Machine Translation of Morphologically Rich Languages

We propose a language-independent approach for improving statistical mac...
research
05/15/2019

Towards Interlingua Neural Machine Translation

A common intermediate language representation or an interlingua is the h...
research
10/21/2020

Deciphering Undersegmented Ancient Scripts Using Phonetic Prior

Most undeciphered lost languages exhibit two characteristics that pose s...

Please sign up or login with your details

Forgot password? Click here to reset