Joint Training for Neural Machine Translation

This book presents four approaches to jointly training bidirectional neural machine translation (NMT) models. First, in order to improve the accuracy of the attention mechanism, it proposes an agreement-based joint training approach to help the two complementary models agree on word alignment matrices for the same training data. Second, it presents a semi-supervised approach that uses an autoencoder to reconstruct monolingual corpora, so as to incorporate these corpora into neural machine translation. It then introduces a joint training algorithm for pivot-based neural machine translation, which can be used to mitigate the data scarcity problem. Lastly it describes an end-to-end bidirectional NMT model to connect the source-to-target and target-to-source translation models, allowing the interaction of parameters between these two directional models.

Nominated by Tsinghua University as an outstanding Ph.D. thesis Reports on current challenges and important advances in neural machine translation Addresses training jointly bidirectional neural machine translation models Incorporates additional monolingual and bilingual corpora into neural machine translation

Autorentext
Yong Cheng is currently a software engineer engaged in research at Google. Before joining Google, he worked as a senior researcher at Tencent AI Lab. He obtained his Ph.D. from the Institute for Interdisciplinary Information Sciences (IIIS) at Tsinghua University in 2017. His research interests focus on neural machine translation and natural language processing.

Inhalt

1. Introduction.- 2. Neural Machine Translation.- 3. Agreement-based Joint Training for Bidirectional Attention-based Neural Machine Translation.- 4. Semi-supervised Learning for Neural Machine Translation.- 5. Joint Training for Pivot-based Neural Machine Translation.- 6. Joint Modeling for Bidirectional Neural Machine Translation with Contrastive Learning.- 7. Related Work.- 8. Conclusion. <p