Neural Machine Translation by Jointly Learning to Align and Translate

09/01/2014
by   Dzmitry Bahdanau, et al.
0

Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. The models proposed recently for neural machine translation often belong to a family of encoder-decoders and consists of an encoder that encodes a source sentence into a fixed-length vector from which a decoder generates a translation. In this paper, we conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and propose to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly. With this new approach, we achieve a translation performance comparable to the existing state-of-the-art phrase-based system on the task of English-to-French translation. Furthermore, qualitative analysis reveals that the (soft-)alignments found by the model agree well with our intuition.

READ FULL TEXT
research
09/29/2015

Neural-based machine translation for medical text domain. Based on European Medicines Agency leaflet texts

The quality of machine translation is rapidly evolving. Today one can fi...
research
08/16/2016

An Efficient Character-Level Neural Machine Translation

Neural machine translation aims at building a single large neural networ...
research
07/03/2016

Context-Dependent Word Representation for Neural Machine Translation

We first observe a potential weakness of continuous vector representatio...
research
12/08/2017

Sequence to Sequence Networks for Roman-Urdu to Urdu Transliteration

Neural Machine Translation models have replaced the conventional phrase ...
research
03/06/2015

Encoding Source Language with Convolutional Neural Network for Machine Translation

The recently proposed neural network joint model (NNJM) (Devlin et al., ...
research
10/15/2018

Learning to Jointly Translate and Predict Dropped Pronouns with a Shared Reconstruction Mechanism

Pronouns are frequently omitted in pro-drop languages, such as Chinese, ...
research
11/07/2016

A Convolutional Encoder Model for Neural Machine Translation

The prevalent approach to neural machine translation relies on bi-direct...

Please sign up or login with your details

Forgot password? Click here to reset