%0 Conference Proceedings %T ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference %A Hui, Kai %A Zhuang, Honglei %A Chen, Tao %A Qin, Zhen %A Lu, Jing %A Bahri, Dara %A Ma, Ji %A Gupta, Jai %A Nogueira dos Santos, Cicero %A Tay, Yi %A Metzler, Donald %Y Muresan, Smaranda %Y Nakov, Preslav %Y Villavicencio, Aline %S Findings of the Association for Computational Linguistics: ACL 2022 %D 2022 %8 May %I Association for Computational Linguistics %C Dublin, Ireland %F hui-etal-2022-ed2lm %X State-of-the-art neural models typically encode document-query pairs using cross-attention for re-ranking. To this end, models generally utilize an encoder-only (like BERT) paradigm or an encoder-decoder (like T5) approach. These paradigms, however, are not without flaws, i.e., running the model on all query-document pairs at inference-time incurs a significant computational cost. This paper proposes a new training and inference paradigm for re-ranking. We propose to finetune a pretrained encoder-decoder model using in the form of document to query generation. Subsequently, we show that this encoder-decoder architecture can be decomposed into a decoder-only language model during inference. This results in significant inference time speedups since the decoder-only architecture only needs to learn to interpret static encoder embeddings during inference. Our experiments show that this new paradigm achieves results that are comparable to the more expensive cross-attention ranking approaches while being up to 6.8X faster. We believe this work paves the way for more efficient neural rankers that leverage large pretrained models. %R 10.18653/v1/2022.findings-acl.295 %U https://aclanthology.org/2022.findings-acl.295 %U https://doi.org/10.18653/v1/2022.findings-acl.295 %P 3747-3758