PASH at TREC 2021 Deep Learning Track: Generative Enhanced Model for Multi-stage Ranking
This work addresses ranking challenges in information retrieval for search systems, but it is incremental as it builds on existing methods with minor enhancements.
The paper tackled multi-stage ranking for information retrieval by combining sparse and dense retrieval with point-wise and pair-wise strategies, and introduced a T5 generative model, achieving enhanced performance compared to TREC 2020 results.
This paper describes the PASH participation in TREC 2021 Deep Learning Track. In the recall stage, we adopt a scheme combining sparse and dense retrieval method. In the multi-stage ranking phase, point-wise and pair-wise ranking strategies are used one after another based on model continual pre-trained on general knowledge and document-level data. Compared to TREC 2020 Deep Learning Track, we have additionally introduced the generative model T5 to further enhance the performance.