A Framework for the Construction of Monolingual and Cross-lingual Word Similarity Datasets

Despite being one of the most popular tasks in lexical semantics, word similar-ity has often been limited to the English language. Other languages, even those that are widely spoken such as Span-ish, do not have a reliable word similar-ity evaluation framework. We put for-ward robust methodologies for the ex-tension of existing English datasets to other languages, both at monolingual and cross-lingual levels. We propose an au-tomatic standardization for the construc-tion of cross-lingual similarity datasets, and provide an evaluation, demonstrating its reliability and robustness. Based on our procedure and taking the RG-65 word similarity dataset as a reference, we re-lease two high-quality Spanish and Farsi (Persian) monolingual datasets, and fifteen cross-lingual datasets for six languages