Encouraging Neural Machine Translation to Satisfy Terminology Constraints

06/07/2021
by   Melissa Ailem, et al.
0

We present a new approach to encourage neural machine translation to satisfy lexical constraints. Our method acts at the training step and thereby avoiding the introduction of any extra computational overhead at inference step. The proposed method combines three main ingredients. The first one consists in augmenting the training data to specify the constraints. Intuitively, this encourages the model to learn a copy behavior when it encounters constraint terms. Compared to previous work, we use a simplified augmentation strategy without source factors. The second ingredient is constraint token masking, which makes it even easier for the model to learn the copy behavior and generalize better. The third one, is a modification of the standard cross entropy loss to bias the model towards assigning high probabilities to constraint words. Empirical results show that our method improves upon related baselines in terms of both BLEU score and the percentage of generated constraint terms.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/03/2021

Lingua Custodia's participation at the WMT 2021 Machine Translation using Terminologies shared task

This paper describes Lingua Custodia's submission to the WMT21 shared ta...
research
10/11/2020

Lexically Cohesive Neural Machine Translation with Copy Mechanism

Lexically cohesive translations preserve consistency in word choices in ...
research
08/07/2023

Negative Lexical Constraints in Neural Machine Translation

This paper explores negative lexical constraining in English to Czech ne...
research
04/27/2020

Lexically Constrained Neural Machine Translation with Levenshtein Transformer

This paper proposes a simple and effective algorithm for incorporating l...
research
08/13/2019

Neural Machine Translation with Noisy Lexical Constraints

Lexically constrained decoding for machine translation has shown to be b...
research
05/27/2023

Disambiguated Lexically Constrained Neural Machine Translation

Lexically constrained neural machine translation (LCNMT), which controls...
research
12/16/2016

Neural Networks Classifier for Data Selection in Statistical Machine Translation

We address the data selection problem in statistical machine translation...

Please sign up or login with your details

Forgot password? Click here to reset