Translation Prediction with Source Dependency-Based Context Representation

Abstract

Learning context representations is very promising to improve translation results, particularly through neural networks. Previous efforts process the context words sequentially and neglect their internal syntactic structure. In this paper, we propose a novel neural network based on bi-convolutional architecture to represent the source dependency-based context for translation prediction. The proposed model is able to not only encode the long-distance dependencies but also capture the functional similarities for better translation prediction (i.e., ambiguous words translation and word forms translation). Examined by a large-scale Chinese-English translation task, the proposed approach achieves a significant improvement (of up to +1.9 BLEU points) over the baseline system, and meanwhile outperforms a number of context-enhanced comparison system.

Training and Evaluating Improved Dependency-Based Word Embeddings

“…The embeddings can significantly improve the CRF based aspect term extraction 1 . In addition, the embedding with SDP based contexts can also be used to improve neural machine translation (Eriguchi, Hashimoto, and Tsuruoka 2016;Chen et al 2017). There have been also other dependency-based embeddings to improve other NLP tasks, such as NER, natural language understanding, and question answering (Jie, Muis, and Lu 2017;Roy and Roth 2017;Xiang et al 2016).…”