The Power of Selecting Key Blocks with Local Pre-ranking for Long Document Information Retrieval

Abstract

On a wide range of natural language processing and information retrieval tasks, transformer-based models, particularly pre-trained language models like BERT, have demonstrated tremendous effectiveness. Due to the quadratic complexity of the self-attention mechanism, however, such models have difficulties processing long documents. Recent works dealing with this issue include truncating long documents, in which case one loses potential relevant information, segmenting them into several passages, which may lead to miss some information and high computational complexity when the number of passages is large, or modifying the self-attention mechanism to make it sparser as in sparse-attention models, at the risk again of missing some information. We follow here a slightly different approach in which one first selects key blocks of a long document by local query-block pre-ranking, and then few blocks are aggregated to form a short document that can be processed by a model such as BERT. Experiments conducted on standard Information Retrieval datasets demonstrate the effectiveness of the proposed approach.

34 pages, accepted by ACM Transactions on Information Systems (TOIS)

References in corpus (12)

• Longformer: The Long-Document Transformer
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• A Deep Relevance Matching Model for Ad-hoc Retrieval
• End-to-End Neural Ad-hoc Ranking with Kernel Pooling
• Generating Long Sequences with Sparse Transformers
• Deeper Text Understanding for IR with Contextual Neural Language Modeling
• Big Bird: Transformers for Longer Sequences
• Overview of the TREC 2020 deep learning track
• Overview of the TREC 2019 deep learning track
• PARADE: Passage Representation Aggregation for Document Reranking
• Neural Passage Retrieval with Improved Negative Contrast
• Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking

Cited by in corpus (1)

• Neural Natural Language Processing for Long Texts: A Survey on Classification and Summarization