Abstract
This paper studies strategies to model word formation in NMT using rich linguistic information, namely a word segmentation approach that goes beyond splitting into substrings by considering fusional morphology. Our linguistically sound segmentation is combined with a method for target-side inflection to accommodate modeling word formation. The best system variants employ source-side morphological analysis and model complex target-side words, improving over a standard system.
Item Type: | Journal article |
---|---|
Faculties: | Languages and Literatures > Department 2 |
Subjects: | 400 Language > 400 Language |
Language: | English |
Item ID: | 88709 |
Date Deposited: | 25. Jan 2022, 09:28 |
Last Modified: | 25. Jan 2022, 09:28 |