Dataset Groups Activity Stream MultiLexNorm dataset The MultiLexNorm dataset is used to evaluate the robustness of MT models to lexical normalization. BibTex: @dataset{Ben_Peters_and_André_F_T_Martins_2024, abstract = {The MultiLexNorm dataset is used to evaluate the robustness of MT models to lexical normalization.}, author = {Ben Peters and André F. T. Martins}, doi = {10.57702/5rgn5hv9}, institution = {No Organization}, keyword = {'MultiLexNorm', 'lexical normalization', 'robustness'}, month = {dec}, publisher = {TIB}, title = {MultiLexNorm dataset}, url = {https://service.tib.eu/ldmservice/dataset/multilexnorm-dataset}, year = {2024} }
