DeepAI AI Chat
Log In Sign Up

Morphology Generation for Statistical Machine Translation using Deep Learning Techniques

10/07/2016
by   Marta R. Costa-Jussà, et al.
Universitat Politècnica de Catalunya
0

Morphology in unbalanced languages remains a big challenge in the context of machine translation. In this paper, we propose to de-couple machine translation from morphology generation in order to better deal with the problem. We investigate the morphology simplification with a reasonable trade-off between expected gain and generation complexity. For the Chinese-Spanish task, optimum morphological simplification is in gender and number. For this purpose, we design a new classification architecture which, compared to other standard machine learning techniques, obtains the best results. This proposed neural-based architecture consists of several layers: an embedding, a convolutional followed by a recurrent neural network and, finally, ends with sigmoid and softmax layers. We obtain classification results over 98 in gender classification, over 93 translation improvement of 0.7 METEOR.

READ FULL TEXT

page 2

page 3

page 4

page 5

page 6

page 7

page 8

page 9

01/02/2020

Morphological Word Segmentation on Agglutinative Languages for Neural Machine Translation

Neural machine translation (NMT) has achieved impressive performance on ...
09/02/2021

How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?

Data-driven subword segmentation has become the default strategy for ope...
07/10/2020

Numerical simulation, clustering and prediction of multi-component polymer precipitation

Multi-component polymer systems are of interest in organic photovoltaic ...
11/08/2021

A Comparison of Deep Learning Architectures for Optical Galaxy Morphology Classification

The classification of galaxy morphology plays a crucial role in understa...
10/05/2017

Morphology Generation for Statistical Machine Translation

When translating into morphologically rich languages, Statistical MT app...
11/26/2020

Data-Efficient Classification of Radio Galaxies

The continuum emission from radio galaxies can be generally classified i...
03/16/2020

Learnergy: Energy-based Machine Learners

Throughout the last years, machine learning techniques have been broadly...

Code Repositories