Long Document Re-ranking with Modular Re-ranker

Abstract

Long document re-ranking has been a challenging problem for neural re-rankers based on deep language models like BERT. Early work breaks the documents into short passage-like chunks. These chunks are independently mapped to scalar scores or latent vectors, which are then pooled into a final relevance score. These encode-and-pool methods however inevitably introduce an information bottleneck: the low dimension representations. In this paper, we propose instead to model full query-to-document interaction, leveraging the attention operation and modular Transformer re-ranker framework. First, document chunks are encoded independently with an encoder module. An interaction module then encodes the query and performs joint attention from the query to all document chunk representations. We demonstrate that the model can use this new degree of freedom to aggregate important information from the entire document. Our experiments show that this design produces effective re-ranking on two classical IR collections Robust04 and ClueWeb09, and a large-scale supervised collection MS-MARCO document ranking.

arXiv commentSIGIR 22

References in corpus (6)

• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• Deeper Text Understanding for IR with Contextual Neural Language Modeling
• Critically Examining the "Neural Hype": Weak Baselines and the Additivity of Effectiveness Gains from Neural Ranking Models
• Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval
• PARADE: Passage Representation Aggregation for Document Reranking
• Query-driven Segment Selection for Ranking Long Documents