Multitask Learning For Different Subword Segmentations In Neural Machine Translation

10/27/2019
by   Tejas Srinivasan, et al.
0

In Neural Machine Translation (NMT) the usage of subwords and characters as source and target units offers a simple and flexible solution for translation of rare and unseen words. However, selecting the optimal subword segmentation involves a trade-off between expressiveness and flexibility, and is language and dataset-dependent. We present Block Multitask Learning (BMTL), a novel NMT architecture that predicts multiple targets of different granularities simultaneously, removing the need to search for the optimal segmentation strategy. Our multi-task model exhibits improvements of up to 1.7 BLEU points on each decoder over single-task baseline models with the same number of parameters on datasets from two language pairs of IWSLT15 and one from IWSLT19. The multiple hypotheses generated at different granularities can be combined as a post-processing step to give better translations, which improves over hypothesis combination from baseline models while using substantially fewer parameters.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/17/2016

Pre-Translation for Neural Machine Translation

Recently, the development of neural machine translation (NMT) has signif...
research
07/07/2016

Neural Name Translation Improves Neural Machine Translation

In order to control computational complexity, neural machine translation...
research
10/06/2020

On the Sparsity of Neural Machine Translation Models

Modern neural machine translation (NMT) models employ a large number of ...
research
11/01/2018

Language-Independent Representor for Neural Machine Translation

Current Neural Machine Translation (NMT) employs a language-specific enc...
research
11/25/2019

Learning to Reuse Translations: Guiding Neural Machine Translation with Examples

In this paper, we study the problem of enabling neural machine translati...
research
12/30/2020

Synthetic Source Language Augmentation for Colloquial Neural Machine Translation

Neural machine translation (NMT) is typically domain-dependent and style...
research
06/07/2019

Shared-Private Bilingual Word Embeddings for Neural Machine Translation

Word embedding is central to neural machine translation (NMT), which has...

Please sign up or login with your details

Forgot password? Click here to reset