“…As a consequence, none of the systems that participated in the SemEval task managed to beat the accuracy of the "All Simple" baseline which labeled all words in the test set as simple (0.953). As noted by Paetzold and Specia (2016), the inverse problem is present in the corpus developed by Shardlow (2013b), where the "All Complex" baseline 6 The word2vec training parameters we use are a context window of size 3, learning rate alpha from 0.025 to 0.0001, minimum word count 100, sampling parameter 1e −4 , 10 negative samples per target word, and 5 training epochs. achieved higher accuracy, recall and F-scores than all other tested systems, suggesting that marking all words in a sentence as complex is the most effective approach for CWI.…”