Reranking Passages with Coarse-to-Fine Neural Retriever Enhanced by List-Context Information

arXiv:2308.12022v2 Announce Type: replace
Abstract: Passage reranking is a critical task in various applications, particularly when dealing with large volumes of documents. Existing neural architectures have limitations in retrieving the most relevant passage for a given question because the semantics of the segmented passages are often incomplete, and they typically match the question to each passage individually, rarely considering contextual information from other passages that could provide comparative and reference information. This paper presents a list-context attention mechanism to augment …

abstract applications architectures arxiv context cs.cl documents information limitations list neural architectures question semantics type