2018/01/11 by Kai Song, Song, Kai, Yue Zhang +5
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.1801.03615
8 pages, 3 figures, 5 tables
arxiv created 2018/01/11 · openalex publication_date 2018/01/11 · arxiv updated 2018/01/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Neural machine translation (NMT) suffers a performance deficiency when a limited vocabulary fails to cover the source or target side adequately, which happens frequently when dealing with morphologically rich languages. To address this problem, previous work focused on adjusting translation granularity or expanding the vocabulary size. However, morphological information is relatively under-considered in NMT architectures, which may further improve translation quality. We propose a novel method, which can not only reduce data sparsity but also model morphology through a simple but effective mechanism. By predicting the stem and suffix separately during decoding, our system achieves an improvement of up to 1.98 BLEU compared with previous work on English to Russian translation. Our method is orthogonal to different NMT architectures and stably gains improvements on various domains.