2020/11/24 by Parnia Bahar, Bahar, Parnia, Christopher Brix +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2011.12165
openalex publication_date 2020/11/24 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Neural translation models have proven to be effective in capturing sufficient\ninformation from a source sentence and generating a high-quality target\nsentence. However, it is not easy to get the best effect for bidirectional\ntranslation, i.e., both source-to-target and target-to-source translation using\na single model. If we exclude some pioneering attempts, such as multilingual\nsystems, all other bidirectional translation approaches are required to train\ntwo individual models. This paper proposes to build a single end-to-end\nbidirectional translation model using a two-dimensional grid, where the\nleft-to-right decoding generates source-to-target, and the bottom-to-up\ndecoding creates target-to-source output. Instead of training two models\nindependently, our approach encourages a single network to jointly learn to\ntranslate in both directions. Experiments on the WMT 2018\nGerman\↔English and Turkish\↔English translation\ntasks show that the proposed model is capable of generating a good translation\nquality and has sufficient potential to direct the research.\n