Tailoring Neural Architectures for Translating from Morphologically Rich Languages

5256

Authors

nan

Abstract

AbstractA morphologically complex word (MCW) is a hierarchical constituent with meaning-preserving subunits, so word-based models which rely on surface forms might not be powerful enough to translate such structures. When translating from morphologically rich languages (MRLs), a source word could be mapped to several words or even a full sentence on the target side, which means an MCW should not be treated as an atomic unit. In order to provide better translations for MRLs, we boost the existing neural machine translation (NMT) architecture with a double- channel encoder and a double-attentive decoder. The main goal targeted in this research is to provide richer information on the encoder side and redesign the decoder accordingly to benefit from such information. Our experimental results demonstrate that we could achieve our goal as the proposed model outperforms existing subword- and character-based architectures and showed significant improvements on translating from German, Russian, and Turkish into English.

Keywords

nan

Full Content

Proceedings of the 27th International Conference on Computational Linguistics, pages 3134–3145 Santa Fe, New Mexico, USA, August 20-26, 2018. 3134 Tailoring Neural Architectures for Translating from Morphologically Rich Languages Peyman Passban, Andy Way, Qun Liu ADAPT Centre School of Computing Dublin City University, Ireland firstname.lastname@adaptcentre.ie Abstract A morphologically complex word (MCW) is a hierarchical constituent with meaning-preserving subunits, so word-based models which rely on surface forms might not be powerful enough to translate such structures. When translating from morphologically rich languages (MRLs), a source word could be mapped to several words or even a full sentence on the target side, which means an MCW should not be treated as an atomic unit. In order to provide better translations for MRLs, we boost the existing neural machine translation (NMT) architecture with a double- channel encoder and a double-attentive decoder. The main goal targeted in this research is to provide richer information on the encoder side and redesign the decoder accordingly to beneﬁt from such information. Our experimental results demonstrate that we could achieve our goal as the proposed model outperforms existing subword- and character-based architectures and showed signiﬁcant improvements on translating from German, Russian, and Turkish into English. Title and Abstract in Farsi (Persian) �� (Encoder-Decoder) �� (Attention mechanism) �� …

Content truncated to 500 words

Labeled Text

Publication Details

Paper ID:: 5256
Year:: 2018
Publication:: TIPSTER
Publication Type:: conf
DOI:: nan

Links

Paper URL PDF Publication URL