|
|
|
Wenhao Zhu, Xiaoyu Zhang, Qiuhong Zhai and Chenyun Liu
In the two-stage open-domain question answering (OpenQA) systems, the retriever identifies a subset of relevant passages, which the reader then uses to extract or generate answers. However, the performance of OpenQA systems is often hindered by issues su...
ver más
|
|
|
|
|
|
|
Qiuhong Zhai, Wenhao Zhu, Xiaoyu Zhang and Chenyun Liu
In recent years, dense retrieval has emerged as the primary method for open-domain question-answering (OpenQA). However, previous research often focused on the query side, neglecting the importance of the passage side. We believe that both the query and ...
ver más
|
|
|
|
|
|
|
Shariq Bashir
Cluster-based pseudo-relevance feedback (PRF) is an effective approach for searching relevant documents for relevance feedback. Standard approach constructs clusters for PRF only on the basis of high similarity between retrieved documents. The standard a...
ver más
|
|
|
|