Recursive Neural Network Based Preordering for English-to-Japanese Machine Translation

2018/05/25 by Yuki Kawara, Kawara, Yuki, Chenhui Chu +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Natural Language Processing Techniques #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.1805.10187

ACL-SRW 2018. 7 pages, 4 figures

arxiv created 2018/05/25 · openalex publication_date 2018/05/25 · arxiv updated 2018/05/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The word order between source and target languages significantly influences the translation quality in machine translation. Preordering can effectively address this problem. Previous preordering methods require a manual feature design, making language dependent design costly. In this paper, we propose a preordering method with a recursive neural network that learns features from raw inputs. Experiments show that the proposed method achieves comparable gain in translation quality to the state-of-the-art method but without a manual feature design.

Citations

• A NEW MEASURE OF RANK CORRELATION
• Effective Approaches to Attention-based Neural Machine Translation

Related

• Simultaneous Neural Machine Translation with Constituent Label Prediction
• Explicit Reordering for Neural Machine Translation
• A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings
• Pre-Translation for Neural Machine Translation
• English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructor