Are Multilingual Neural Machine Translation Models Better at Capturing Linguistic Features?

Linguistic Input Features Improve Neural Machine Translation

Neural machine translation has recently achieved impressive results, while using little in the way of external linguistic information. In this paper we show that the strong learning capability of neural MT models does not make linguistic features redundant; they can be easily incorporated to provide further improvements in performance. We generalize the embedding layer of the encoder in the att...

Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation

We propose a simple solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages. Our solution requires no changes to the model architecture from a standard NMT system but instead introduces an artificial token at the beginning of the input sentence to specify the required target language. The rest of the model, which includes an encoder, decoder and a...

Applications in Multilingual Machine Translation Applications in Multilingual Machine Translation

The CAT2 Machine Translation System, developed in Saarbr ucken in 1987, is a natural language application coded entirely in Prolog. Since its initial development, several languages have been implemented on an experimental basis to evaluate the translation methodology, the underlying formalism, the linguistic descriptions, and the e ectiveness of the Prolog implementation. Seven years later, it...

Build Better Business Models for Machine Translation

Better Statistical Machine Translation through Linguistic Treatment of Phrasal Verbs

This article describes a linguistically informed method for integrating phrasal verbs into statistical machine translation (SMT) systems. In a case study involving English to Bulgarian SMT, we show that our method does not only improve translation quality but also outperforms similar methods previously applied to the same task. We attribute this to the fact that, in contrast to previous work on...