DeepAI
Log In Sign Up

Capturing Longer Context for Document-level Neural Machine Translation: A Multi-resolutional Approach

10/18/2020
by   Zewei Sun, et al.
0

Discourse context has been proven useful when translating documents. It is quite a challenge to incorporate long document context in the prevailing neural machine translation models such as Transformer. In this paper, we propose multi-resolutional (MR) Doc2Doc, a method to train a neural sequence-to-sequence model for document-level translation. Our trained model can simultaneously translate sentence by sentence as well as a document as a whole. We evaluate our method and several recent approaches on nine document-level datasets and two sentence-level datasets across six languages. Experiments show that MR Doc2Doc outperforms sentence-level models and previous methods in a comprehensive set of metrics, including BLEU, four lexical indices, three newly proposed assistant linguistic indicators, and human evaluation.

READ FULL TEXT

page 1

page 2

page 3

page 4

08/19/2022

Discourse Cohesion Evaluation for Document-Level Neural Machine Translation

It is well known that translations generated by an excellent document-le...
04/16/2021

Context-Adaptive Document-Level Neural Machine Translation

Most existing document-level neural machine translation (NMT) models lev...
02/19/2020

Toward Making the Most of Context in Neural Machine Translation

Document-level machine translation manages to outperform sentence level ...
05/04/2020

Using Context in Neural Machine Translation Training Objectives

We present Neural Machine Translation (NMT) training using document-leve...
10/16/2022

Modeling Context With Linear Attention for Scalable Document-Level Translation

Document-level machine translation leverages inter-sentence dependencies...
01/05/2022

SMDT: Selective Memory-Augmented Neural Document Translation

Existing document-level neural machine translation (NMT) models have suf...
09/19/2020

Long-Short Term Masking Transformer: A Simple but Effective Baseline for Document-level Neural Machine Translation

Many document-level neural machine translation (NMT) systems have explor...

Code Repositories

Doc2Doc_NMT

The repository for the paper: Capturing Longer Context for Document-level Neural Machine Translation – A Multi-resolutional Approach


view repo