COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
This work addresses the need for more efficient and accurate pretraining methods for natural language processing tasks, offering incremental improvements over existing approaches like ELECTRA.
The paper tackles the problem of improving language model pretraining efficiency and accuracy by introducing COCO-LM, a framework that corrects and contrasts corrupted text sequences, achieving a 50% reduction in GPU hours compared to ELECTRA while outperforming previous models by over 1 point on GLUE.
We present a self-supervised learning framework, COCO-LM, that pretrains Language Models by COrrecting and COntrasting corrupted text sequences. Following ELECTRA-style pretraining, COCO-LM employs an auxiliary language model to corrupt text sequences, upon which it constructs two new tasks for pretraining the main model. The first token-level task, Corrective Language Modeling, is to detect and correct tokens replaced by the auxiliary model, in order to better capture token-level semantics. The second sequence-level task, Sequence Contrastive Learning, is to align text sequences originated from the same source input while ensuring uniformity in the representation space. Experiments on GLUE and SQuAD demonstrate that COCO-LM not only outperforms recent state-of-the-art pretrained models in accuracy, but also improves pretraining efficiency. It achieves the MNLI accuracy of ELECTRA with 50% of its pretraining GPU hours. With the same pretraining steps of standard base/large-sized models, COCO-LM outperforms the previous best models by 1+ GLUE average points.