Empirical Analysis of Parallel Corpora and In-Depth Analysis Using LIWC

The machine translation system aims to translate source language into target language. Recent studies on MT systems mainly focus neural translation. One factor that significantly affects the performance of NMT is availability high-quality parallel corpora. However, corpora concerning Korean are relatively scarce compared those associated with other high-resource languages, such as German or Italian. To address this problem, AI Hub recently released seven types for Korean. In study, we conduct an in-depth verification quality corresponding through Linguistic Inquiry and Word Count (LIWC) several relevant experiments. LIWC a word-counting software program can analyze in multiple ways extract linguistic features dictionary base. best our knowledge, study first use field NMT. Our findings suggest direction further research toward obtaining improved correlation analysis performance.