We have just released Multi-SimLex v1: a new multilingual #NLProc resource for semantic similarity. It covers 1,888 concept pairs across 12 typologically diverse langs, plus 66 xling data sets. .
https://multisimlex.com
Multi-SimLex provides a new, typologically diverse evaluation benchmark for representation learning models. See our paper for experiments and interesting analysis:
https://arxiv.org/pdf/2003.04866.pdf
But this is not all! We are also launching a collaborative initiative to extend Multi-SimLex to cover many more of the world’s languages! Please join us in this effort to create an extensive semantic similarity resource for the needs of contemporary multilingual #NLProc.We welcome your contributions for both small and major languages! Follow the guidelines at https://multisimlex.com to create and submit a Multi-Simlex -style dataset for your favourite language. All the
contributions will be shared with everyone via the Multi-SimLex site.
https://multisimlex.com
Multi-SimLex provides a new, typologically diverse evaluation benchmark for representation learning models. See our paper for experiments and interesting analysis:
https://arxiv.org/pdf/2003.04866.pdf
But this is not all! We are also launching a collaborative initiative to extend Multi-SimLex to cover many more of the world’s languages! Please join us in this effort to create an extensive semantic similarity resource for the needs of contemporary multilingual #NLProc.We welcome your contributions for both small and major languages! Follow the guidelines at https://multisimlex.com to create and submit a Multi-Simlex -style dataset for your favourite language. All the
contributions will be shared with everyone via the Multi-SimLex site.