Multilingual Transitivity and Bidirectional Multilingual Agreement for Multilingual Document-level Machine Translation

by   Hongyuan Lu, et al.

Multilingual machine translation has been proven an effective strategy to support translation between multiple languages with a single model. However, most studies focus on multilingual sentence translation without considering generating long documents across different languages, which requires an understanding of multilingual context dependency and is typically harder. In this paper, we first spot that naively incorporating auxiliary multilingual data either auxiliary-target or source-auxiliary brings no improvement to the source-target language pair in our interest. Motivated by this observation, we propose a novel framework called Multilingual Transitivity (MTrans) to find an implicit optimal route via source-auxiliary-target within the multilingual model. To encourage MTrans, we propose a novel method called Triplet Parallel Data (TPD), which uses parallel triplets that contain (source-auxiliary, auxiliary-target, and source-target) for training. The auxiliary language then serves as a pivot and automatically facilitates the implicit information transition flow which is easier to translate. We further propose a novel framework called Bidirectional Multilingual Agreement (Bi-MAgree) that encourages the bidirectional agreement between different languages. To encourage Bi-MAgree, we propose a novel method called Multilingual Kullback-Leibler Divergence (MKL) that forces the output distribution of the inputs with the same meaning but in different languages to be consistent with each other. The experimental results indicate that our methods bring consistent improvements over strong baselines on three document translation tasks: IWSLT2015 Zh-En, De-En, and Vi-En. Our analysis validates the usefulness and existence of MTrans and Bi-MAgree, and our frameworks and methods are effective on synthetic auxiliary data.


page 1

page 2

page 3

page 4


Multilingual Speech-to-Speech Translation into Multiple Target Languages

Speech-to-speech translation (S2ST) enables spoken communication between...

Paraphrases as Foreign Languages in Multilingual Neural Machine Translation

Using paraphrases, the expression of the same semantic meaning in differ...

A Multilingual View of Unsupervised Machine Translation

We present a probabilistic framework for multilingual neural machine tra...

UM4: Unified Multilingual Multiple Teacher-Student Model for Zero-Resource Neural Machine Translation

Most translation tasks among languages belong to the zero-resource trans...

Two-Way Neural Machine Translation: A Proof of Concept for Bidirectional Translation Modeling using a Two-Dimensional Grid

Neural translation models have proven to be effective in capturing suffi...

Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation

Despite advances in multilingual neural machine translation (MNMT), we a...

Alternative Input Signals Ease Transfer in Multilingual Machine Translation

Recent work in multilingual machine translation (MMT) has focused on the...

Please sign up or login with your details

Forgot password? Click here to reset