Augmenting Neural Machine Translation with Knowledge Graphs

By Diego Moussallem, Mihael Arcan, Axel-Cyrille Ngonga Ngomo, Paul Buitelaar. 2019

27 citations recorded by the source corpus.

While neural networks have been used extensively to make substantial progress in the machine translation task, they are known for being heavily dependent on the availability of large amounts of training data. Recent efforts have tried to alleviate the data sparsity problem by augmenting the training data using different strategies, such as back-translation. Along with the data scarcity, the out-of-vocabulary words, mostly entities and terminological expressions, pose a difficult challenge to Neural Machine Translation systems. In this paper, we hypothesize that knowledge graphs enhance the semantic feature extraction of neural models, thus optimizing the translation of entities and terminological expressions in texts and consequently leading to a better translation quality. We hence investigate two different strategies for incorporating knowledge graphs into neural models without modifying the neural network architectures. We also examine the effectiveness of our augmentation method to recurrent and non-recurrent (self-attentional) neural architectures. Our knowledge graph augmented neural translation model, dubbed KG-NMT, achieves significant and consistent improvements of +3 BLEU, METEOR and chrF3 on average on the newstest datasets between 2014 and 2018 for WMT English-German translation task.

Subfields: Artificial Intelligence, 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 Natural Language Processing

Citations in the corpus

A Survey of Data Augmentation Approaches for NLP (2021, methodology): “Moussallem et al. (2019) Propose an NMT model KG-NMT which is augmented by knowledge graphs to enhance semantic feature extraction and hence the translation of entities and terminological expressions.”
Neural Machine Translation: A Review (2019, methodology): “Lattices have also been used to augment the input with external knowledge sources such as knowledge graphs [587, 588] or semantic predicate-argument structures [589].”