PGT: Pseudo Relevance Feedback Using a Graph-Based Transformer
arXiv:2101.07918
Abstract
Most research on pseudo relevance feedback (PRF) has been done in vector space and probabilistic retrieval models. This paper shows that Transformer-based rerankers can also benefit from the extra context that PRF provides. It presents PGT, a graph-based Transformer that sparsifies attention between graph nodes to enable PRF while avoiding the high computational complexity of most Transformer architectures. Experiments show that PGT improves upon non-PRF Transformer reranker, and it is at least as accurate as Transformer PRF models that use full attention, but with lower computational costs.
arXiv commentAccepted at ECIR 2021 (short paper track)
References in corpus (7)
- Longformer: The Long-Document Transformer
- REALM: Retrieval-Augmented Language Model Pre-Training
- Generating Long Sequences with Sparse Transformers
- Passage Re-ranking with BERT
- Complementing Lexical Retrieval with Semantic Residual Embedding
- Relevance Transformer: Generating Concise Code Snippets with Relevance Feedback
- Overview of the TREC 2022 deep learning track