Creating Bilingual Lexica Using Reference Wordlists for Alignment of Monolingual Semantic Vector Spaces

摘要: This paper proposes a novel method for automatically acquiring multi-lingual lexica from non-parallel data and reports some initial experiments to prove the viability of approach. Using established techniques building mono-lingual vector spaces two independent semantic vector spaces are built textual data. These vector are related each other using small {\em reference word list} manually chosen points taken from available bi-lingual dictionaries. Other words can then be related these first in one language in other. In present experiments, we apply proposed comparable but non-parallel English-German The resulting lexicon is evaluated an online as gold standard. results clearly demonstrate methodology.