Uncertainty-Aware Semantic Augmentation for Neural Machine Translation

10/09/2020
by   Xiangpeng Wei, et al.
0

As a sequence-to-sequence generation task, neural machine translation (NMT) naturally contains intrinsic uncertainty, where a single sentence in one language has multiple valid counterparts in the other. However, the dominant methods for NMT only observe one of them from the parallel corpora for the model training but have to deal with adequate variations under the same meaning at inference. This leads to a discrepancy of the data distribution between the training and the inference phases. To address this problem, we propose uncertainty-aware semantic augmentation, which explicitly captures the universal semantic information among multiple semantically-equivalent source sentences and enhances the hidden representations with this information for better translations. Extensive experiments on various translation tasks reveal that our approach significantly outperforms the strong baselines and the existing methods.

READ FULL TEXT

page 3

page 4

page 5

page 6

page 7

page 9

page 10

page 11

research
02/19/2019

Semantic Neural Machine Translation using AMR

It is intuitive that semantic representations can be useful for machine ...
research
06/21/2020

AdvAug: Robust Adversarial Augmentation for Neural Machine Translation

In this paper, we propose a new adversarial augmentation method for Neur...
research
02/28/2018

Analyzing Uncertainty in Neural Machine Translation

Machine translation is a popular test bed for research in neural sequenc...
research
04/23/2020

Multiple Segmentations of Thai Sentences for Neural Machine Translation

Thai is a low-resource language, so it is often the case that data is no...
research
04/08/2022

C-NMT: A Collaborative Inference Framework for Neural Machine Translation

Collaborative Inference (CI) optimizes the latency and energy consumptio...
research
03/20/2023

Towards Reliable Neural Machine Translation with Consistency-Aware Meta-Learning

Neural machine translation (NMT) has achieved remarkable success in prod...
research
03/29/2018

Identifying Semantic Divergences in Parallel Text without Annotations

Recognizing that even correct translations are not always semantically e...

Please sign up or login with your details

Forgot password? Click here to reset