The Source-Target Domain Mismatch Problem in Machine Translation

By Jiajun Shen, Peng-Jen Chen, Matt Le, Junxian He, Jiatao Gu, Myle Ott, Michael Auli, Marc'Aurelio Ranzato. 2019

28 citations recorded by the source corpus.

While we live in an increasingly interconnected world, different places still exhibit strikingly different cultures and many events we experience in our every day life pertain only to the specific place we live in. As a result, people often talk about different things in different parts of the world. In this work we study the effect of local context in machine translation and postulate that this causes the domains of the source and target language to greatly mismatch. We first formalize the concept of source-target domain mismatch, propose a metric to quantify it, and provide empirical evidence for its existence. We conclude with an empirical study of how source-target domain mismatch affects training of machine translation systems on low resource languages. While this may severely affect back-translation, the degradation can be alleviated by combining back-translation with self-training and by increasing the amount of target side monolingual data.

Subfields: Artificial Intelligence, Language and Linguistics, Natural Language Processing

How researchers see this paper

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

In Artificial Intelligence

In Language and Linguistics

Holger Schwenk

In Natural Language Processing

Citations in the corpus

Beyond English-Centric Multilingual Machine Translation (2020, background): “Further, multilingual translation can be affected by domain mismatch, as people in different parts of the world discuss different topics (Shen et al., 2019), which presents additional challenges for curating good training sets.”
Facebook AI’s WMT20 News Translation Task Submission (2020, result): “Shen et al. (2019); Chen et al. (2019) both show that self-training can provide complementary improvement in addition to back-translation, especially when (1) there is lack of target side monolingual data, (2) source side monolingual data is much similar to the domain of test set compared with…”
Translationese as a Language in “Multilingual” NMT (2019, methodology): “Our NMT models use the transformer-big architecture (Vaswani et al., 2017) implemented in lingvo (Shen et al., 2019) with a shared sourcetarget byte-pair-encoding (BPE) vocabulary (Sen- 3BLEU + case.mixed + lang.”