Cross-lingual Synonymy Overlap

We investigate in this paper the degree of overlap between synonym sets of translated word pairs across three languages: French, English and Romanian. We use for this purpose a French Synonym Dictionary, a Romanian Synonym Dictionary, Princeton’s WordNet and Google Translate API. We build a database containing pairs of (translated) words from the three languages, along with their corresponding synonym sets. We use it in order to gain insight into the synonym overlap for each language pair, and thus, into their degree of common concept lexicalization, by various queries. While the overall percentage of common synonyms is (expectedly) quite small (averaging ~6% across all language pairs), the percentage of hard synonyms pairs (pairs that have at least one common synonym), reaching ~62%, is significant. This is encouraging for further use of this special kind of word translated pairs in tasks such as automatic enhancement of lexical databases (such as WordNet) for less resourced languages such as Romanian, based on corresponding English versions of these lexical databases. Another interesting query topic was obtaining distributions of hard synonym pairs, function of their part of speech: hard synonyms were most frequent among verbs for English, and among adjectives for Romanian and French.