Abstract
The Seq2Seq model and its variants (ConvSeq2Seq and Transformer) emerge as a promising novel solution to the machine translation problem. However, these models only focus on exploiting knowledge from bilingual sentences without paying much attention to utilizing external linguistic knowledge sources such as semantic representations. Not only do semantic representations can help preserve meaning but they also minimize the data sparsity problem. However, to date, semantic information remains rarely integrated into machine translation models. In this study, we examine the effect of abstract meaning representation (AMR) semantic graphs in different machine translation models. Experimental results on the IWSLT15 English-Vietnamese dataset have proven the efficiency of the proposed model, expanding the use of external language knowledge sources to significantly improve the performance of machine translation models, especially in the application of low-resource language pairs.
Highlights
Neural machine translation (NMT) [1,2,3,4] has proven its effectiveness and has gained researchers’ attention in recent years
The typical inputs to NMT systems are sentences in which words are represented as individual vectors in a word embedding space. is word embedding space does not show any connection among words within a sentence such as dependency or semantic role relationships
We present the method of integrating abstract meaning representation (AMR) graphs as additional semantic information into the current popular NMT systems such as Seq2Seq, ConvSeq2Seq, and Transformer
Summary
Neural machine translation (NMT) [1,2,3,4] has proven its effectiveness and has gained researchers’ attention in recent years. We present the method of integrating abstract meaning representation (AMR) graphs (https:// amr.isi.edu) as additional semantic information into the current popular NMT systems such as Seq2Seq, ConvSeq2Seq, and Transformer. Structured semantic information constructed from AMR graphs could help complement the input text by providing high-level abstract information, thereby improving the encoding of the input word embedding. Song et al [10] proved that semantic information structured from AMR graphs can complement input text by incorporating high-level abstract information.
Published Version (Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have