Hierarchical corpus encoder: Fusing generative retrieval and dense indices
Generative retrieval employs sequence models for conditional generation of document IDs based on a query (DSI (Tay et al., 2022); NCI (Wang et al., 2022); inter alia). While this has led to improved performance in zero-shot retrieval, it is a challenge to support documents not seen during training. We identify the performance of generative retrieval lies in contrastive training between sibling nodes in a document hierarchy. This motivates our proposal, the hierarchical corpus encoder (HCE), which can be supported by traditional dense encoders. Our experiments show that HCE achieves superior results than generative retrieval models under both unsupervised zero-shot and supervised settings, while also allowing the easy addition and removal of documents to the index.
Code (0)
등록된 구현이 없습니다.
Tasks
RetrievalSimilar Papers 제목 키워드 기반
Hierarchical Semantic Retrieval with Cobweb
Neural document retrieval often treats a corpus as a flat cloud of vectors scored at a single granularity, leaving corpus structure underused and explanations opaque. We use Cobweb--a hierarchy-aware framework--to organi…
Semantic RetrievalCorpus2Skill: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
Retrieval-Augmented Generation (RAG) grounds LLM responses in external evidence but treats the model as a passive consumer of search results, with no view of how the corpus is organized or what it has not yet seen. We pr…
How Does Generative Retrieval Scale to Millions of Passages?
Popularized by the Differentiable Search Index, the emerging paradigm of generative retrieval re-frames the classic information retrieval problem into a sequence-to-sequence modeling task, forgoing external indices and e…
Information RetrievalPassage RankingRetrievalHierarchical Indexing with Knowledge Enrichment for Multilingual Video Corpus Retrieval
Retrieving relevant instructional videos from multilingual medical archives is crucial for answering complex, multi-hop questions across language boundaries. However, existing systems either compress hour-long videos int…
Get the Point! Graph Enhanced Candidate Retrieval for Zero-shot Entity Linking
For the retrieval phase of the zero-shot entity linking task, BERT has been widely used to represent the mentions and entities with the sentence embeddings. However, the sentence embeddings obtained by BERT are dominated…
Entity LinkingEntity RetrievalGraph Neural NetworkRetrieval+4