From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader
This addresses the discrepancy between pre-training and fine-tuning for MLMs, benefiting NLP practitioners by providing a unified model for extraction and classification tasks, though it is incremental as it builds on existing pre-trained models.
The paper tackles the problem of retrofitting pre-trained masked language models to machine reading comprehension models without labeled data, resulting in PMR, which shows tremendous improvements in low-resource scenarios and enables high-quality rationale extraction for explainability.
We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models without acquiring labeled data. PMR can resolve the discrepancy between model pre-training and downstream fine-tuning of existing MLMs. To build the proposed PMR, we constructed a large volume of general-purpose and high-quality MRC-style training data by using Wikipedia hyperlinks and designed a Wiki Anchor Extraction task to guide the MRC-style pre-training. Apart from its simplicity, PMR effectively solves extraction tasks, such as Extractive Question Answering and Named Entity Recognition. PMR shows tremendous improvements over existing approaches, especially in low-resource scenarios. When applied to the sequence classification task in the MRC formulation, PMR enables the extraction of high-quality rationales to explain the classification process, thereby providing greater prediction explainability. PMR also has the potential to serve as a unified model for tackling various extraction and classification tasks in the MRC formulation.