GMU-WLV at TSAR-2022 Shared Task: Evaluating Lexical Simplification Models
Kai North, Alphaeus Dmonte, Tharindu Ranasinghe, Marcos Zampieri · 2022
This paper describes team GMU-WLV submission to the TSAR shared-task on multilingual lexical simplification.The goal of the task is to automatically provide a set of candidate substitutions for complex words in context.The organizers provided participants with ALEXSIS, a manually annotated lexical simplification dataset in English, Portuguese, and Spanish.Instances in ALEXSIS were split between a small trial set with a dozen instances in each of the three languages of the competition and a test set with over 300 instances in the three aforementioned languages.To cope with the lack of training data, participants had to either use alternative data sources or pre-trained language models.We experimented with monolingual models: BERTimbau, ELECTRA, and RoBERTA-large-BNE.Our best system achieved 1 st place out of sixteen systems for Portuguese, 8 th out of thirty-three systems for English, and 6 th out of twelve systems for Spanish.