Linguistic analysis of non-ITG word reordering between language pairs with different word order typologies

Abstract

The Inversion Transduction Grammar (ITG) constraints have been widely used for word reordering in machine translation studies. They are, however, so restricted that some types of word reordering cannot be handled properly. We analyze three corpora between SVO and SOV languages: Chinese-Korean, English- Japanese, and English-Korean. In our analysis, sentences that require non-ITG word reordering are manually categorized. We also report the results for two quantitative measures that reveal the significance of non-ITG word reordering. In conclusion, we suggest that ITG constraints are insufficient to deal with word reordering in real situations.