Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging.
#2 best model for Natural Language Inference on QNLI
Unlike the previously proposed automated TS systems, our neural text simplification (NTS) systems are able to simultaneously perform lexical simplification and content reduction.
Lexical simplification (LS) aims to replace complex words in a given sentence with their simpler alternatives of equivalent meaning.
Our adversarial post-specialization method propagates the external lexical knowledge to the full distributional space.