Exploring the Use of Attention within an Neural Machine Translation Decoder States to Translate Idioms
Computation and Language
2018-10-17 v1 Machine Learning
Machine Learning
Abstract
Idioms pose problems to almost all Machine Translation systems. This type of language is very frequent in day-to-day language use and cannot be simply ignored. The recent interest in memory augmented models in the field of Language Modelling has aided the systems to achieve good results by bridging long-distance dependencies. In this paper we explore the use of such techniques into a Neural Machine Translation system to help in translation of idiomatic language.
Keywords
Cite
@article{arxiv.1810.06695,
title = {Exploring the Use of Attention within an Neural Machine Translation Decoder States to Translate Idioms},
author = {Giancarlo D. Salton and Robert J. Ross and John D. Kelleher},
journal= {arXiv preprint arXiv:1810.06695},
year = {2018}
}