Exploring the Use of Attention within an Neural Machine Translation Decoder States to Translate Idioms
This addresses a frequent issue in day-to-day language translation, but it appears incremental as it applies existing techniques from language modeling to a specific domain.
The paper tackled the problem of translating idioms in Neural Machine Translation by exploring memory-augmented models, achieving good results in bridging long-distance dependencies for idiomatic language.
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.