Retrieval Oriented Masking Pre-training Language Model for Dense Passage Retrieval

Abstract: Pre-trained LLM (PTM) has been shown to yield powerful text representations for dense passage retrieval task. The Masked Language Modeling (MLM) is a major sub-task of the pre-training process. However, we found that the conventional random masking strategy tend to select a large number of tokens that have limited effect on the passage retrieval task (e,g. stop-words and punctuation). By noticing the term importance weight can provide valuable information for passage retrieval, we hereby propose alternative retrieval oriented masking (dubbed as ROM) strategy where more important tokens will have a higher probability of being masked out, to capture this straightforward yet essential information to facilitate the LLM pre-training process. Notably, the proposed new token masking method will not change the architecture and learning objective of original PTM. Our experiments verify that the proposed ROM enables term importance information to help LLM pre-training thus achieving better performance on multiple passage retrieval benchmarks.