SemEval-2017 Task 2: Multilingual and Cross-lingual Semantic Word Similarity

This competition on Multilingual and Cross-lingual Semantic Word Similarity which measures the semantic similarity of word pairs within and across five languages: English, Farsi, German,
Italian and Spanish. Datasets were manually curated for the five languages, which were used for semi-automatic construction of ten cross-lingual datasets. The competition has
two related tasks: multilingual semantic similarity, which focuses on representation learning for individual languages, and cross-lingual semantic similarity, which provides a benchmark for  multilingual research that learns unified representations for multiple languages.