Text Repair Model for Neural Machine Translation

By Markus Freitag, Isaac Caswell, Scott Roy. 2019

8 citations recorded by the source corpus.

In this work, we train a text repair model as a post-processor for Neural Machine Translation (NMT). The goal of the repair model is to correct typical errors introduced by the translation process, and convert the "translationese" output into natural text. The repair model is trained on monolingual data that has been round-trip translated through English, to mimic errors that are similar to the ones introduced by NMT. Having a trained repair model, we apply it to the output of existing NMT systems. We run experiments for both the WMT18 English to German and the WMT16 English to Romanian task. Furthermore, we apply the repair model on the output of the top submissions of the most recent WMT evaluation campaigns. We see quality improvements on all tasks of up to 2.5 BLEU points.

Subfields: Natural Language Processing, Machine Translation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Machine Translation

Citations in the corpus

Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges (2019, background): “Even so, attention must be paid to the original language (Freitag et al., 2019) and domain such data is collected from.”
Controlling Computation versus Quality for Neural Sequence Models (2020, background): “This might also be explained by the model’s outputs being samples of a smooth marginal distribution that is easier to learn (with much fewer modes), as compared against natural target text (Freitag et al., 2019).”
Levenshtein Transformer (2019, methodology): “Freitag et al. (2019) correct patterned errors in MT system outputs using transformer models trained on monolingual data.”