Using Context in Neural Machine Translation Training Objectives

05/04/2020
by   Danielle Saunders, et al.
0

We present Neural Machine Translation (NMT) training using document-level metrics with batch-level documents. Previous sequence-objective approaches to NMT training focus exclusively on sentence-level metrics like sentence BLEU which do not correspond to the desired evaluation metric, typically document BLEU. Meanwhile research into document-level NMT training focuses on data or model architecture rather than training procedure. We find that each of these lines of research has a clear space in it for the other, and propose merging them with a scheme that allows a document-level evaluation metric to be used in the NMT training objective. We first sample pseudo-documents from sentence samples. We then approximate the expected document BLEU gradient with Monte Carlo sampling for use as a cost function in Minimum Risk Training (MRT). This two-level sampling procedure gives NMT performance gains over sequence MRT and maximum-likelihood training. We demonstrate that training is more robust for document-level metrics than with sequence metrics. We further demonstrate improvements on NMT with TER and Grammatical Error Correction (GEC) using GLEU, both metrics used at the document level for evaluations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/20/2023

Exploring Paracrawl for Document-level Neural Machine Translation

Document-level neural machine translation (NMT) has outperformed sentenc...
research
08/19/2022

Discourse Cohesion Evaluation for Document-Level Neural Machine Translation

It is well known that translations generated by an excellent document-le...
research
02/19/2020

Toward Making the Most of Context in Neural Machine Translation

Document-level machine translation manages to outperform sentence level ...
research
04/15/2021

Reward Optimization for Neural Machine Translation with Learned Metrics

Neural machine translation (NMT) models are conventionally trained with ...
research
04/07/2016

Neural Headline Generation with Sentence-wise Optimization

Recently, neural models have been proposed for headline generation by le...
research
02/11/2021

Towards Personalised and Document-level Machine Translation of Dialogue

State-of-the-art (SOTA) neural machine translation (NMT) systems transla...
research
07/24/2018

Otem&Utem: Over- and Under-Translation Evaluation Metric for NMT

Although neural machine translation(NMT) yields promising translation pe...

Please sign up or login with your details

Forgot password? Click here to reset