Translating Compounds by Learning Component Gloss Translation Models via Multiple Languages

This paper presents an approach to the translation of compound words without the need for bilingual training text, by modeling the mapping of literal component word glosses (e.g. “iron-path”) into fluent English (e.g. “railway”) across multiple languages. Performance is improved by adding component-sequence and learnedmorphology models along with context similarity from monolingual text and optional combination with traditional bilingual-textbased translation discovery.