Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315704974> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4315704974 abstract "Doc2Query -- the process of expanding the content of a document before indexing using a sequence-to-sequence model -- has emerged as a prominent technique for improving the first-stage retrieval effectiveness of search engines. However, sequence-to-sequence models are known to be prone to hallucinating content that is not present in the source text. We argue that Doc2Query is indeed prone to hallucination, which ultimately harms retrieval effectiveness and inflates the index size. In this work, we explore techniques for filtering out these harmful queries prior to indexing. We find that using a relevance model to remove poor-quality queries can improve the retrieval effectiveness of Doc2Query by up to 16%, while simultaneously reducing mean query execution time by 23% and cutting the index size by 33%. We release the code, data, and a live demonstration to facilitate reproduction and further exploration at https://github.com/terrierteam/pyterrier_doc2query." @default.
- W4315704974 created "2023-01-12" @default.
- W4315704974 creator A5014199889 @default.
- W4315704974 creator A5023545439 @default.
- W4315704974 creator A5057643560 @default.
- W4315704974 date "2023-01-09" @default.
- W4315704974 modified "2023-09-27" @default.
- W4315704974 title "Doc2Query--: When Less is More" @default.
- W4315704974 doi "https://doi.org/10.48550/arxiv.2301.03266" @default.
- W4315704974 hasPublicationYear "2023" @default.
- W4315704974 type Work @default.
- W4315704974 citedByCount "0" @default.
- W4315704974 crossrefType "posted-content" @default.
- W4315704974 hasAuthorship W4315704974A5014199889 @default.
- W4315704974 hasAuthorship W4315704974A5023545439 @default.
- W4315704974 hasAuthorship W4315704974A5057643560 @default.
- W4315704974 hasBestOaLocation W43157049741 @default.
- W4315704974 hasConcept C111472728 @default.
- W4315704974 hasConcept C111919701 @default.
- W4315704974 hasConcept C124101348 @default.
- W4315704974 hasConcept C136764020 @default.
- W4315704974 hasConcept C138885662 @default.
- W4315704974 hasConcept C154945302 @default.
- W4315704974 hasConcept C158154518 @default.
- W4315704974 hasConcept C177264268 @default.
- W4315704974 hasConcept C17744445 @default.
- W4315704974 hasConcept C199360897 @default.
- W4315704974 hasConcept C199539241 @default.
- W4315704974 hasConcept C23123220 @default.
- W4315704974 hasConcept C2776760102 @default.
- W4315704974 hasConcept C2777382242 @default.
- W4315704974 hasConcept C2778112365 @default.
- W4315704974 hasConcept C2779530757 @default.
- W4315704974 hasConcept C2911011789 @default.
- W4315704974 hasConcept C41008148 @default.
- W4315704974 hasConcept C54355233 @default.
- W4315704974 hasConcept C75165309 @default.
- W4315704974 hasConcept C86803240 @default.
- W4315704974 hasConcept C98045186 @default.
- W4315704974 hasConceptScore W4315704974C111472728 @default.
- W4315704974 hasConceptScore W4315704974C111919701 @default.
- W4315704974 hasConceptScore W4315704974C124101348 @default.
- W4315704974 hasConceptScore W4315704974C136764020 @default.
- W4315704974 hasConceptScore W4315704974C138885662 @default.
- W4315704974 hasConceptScore W4315704974C154945302 @default.
- W4315704974 hasConceptScore W4315704974C158154518 @default.
- W4315704974 hasConceptScore W4315704974C177264268 @default.
- W4315704974 hasConceptScore W4315704974C17744445 @default.
- W4315704974 hasConceptScore W4315704974C199360897 @default.
- W4315704974 hasConceptScore W4315704974C199539241 @default.
- W4315704974 hasConceptScore W4315704974C23123220 @default.
- W4315704974 hasConceptScore W4315704974C2776760102 @default.
- W4315704974 hasConceptScore W4315704974C2777382242 @default.
- W4315704974 hasConceptScore W4315704974C2778112365 @default.
- W4315704974 hasConceptScore W4315704974C2779530757 @default.
- W4315704974 hasConceptScore W4315704974C2911011789 @default.
- W4315704974 hasConceptScore W4315704974C41008148 @default.
- W4315704974 hasConceptScore W4315704974C54355233 @default.
- W4315704974 hasConceptScore W4315704974C75165309 @default.
- W4315704974 hasConceptScore W4315704974C86803240 @default.
- W4315704974 hasConceptScore W4315704974C98045186 @default.
- W4315704974 hasLocation W43157049741 @default.
- W4315704974 hasOpenAccess W4315704974 @default.
- W4315704974 hasPrimaryLocation W43157049741 @default.
- W4315704974 hasRelatedWork W1584628001 @default.
- W4315704974 hasRelatedWork W1606406758 @default.
- W4315704974 hasRelatedWork W1863997242 @default.
- W4315704974 hasRelatedWork W1873761914 @default.
- W4315704974 hasRelatedWork W1963586751 @default.
- W4315704974 hasRelatedWork W1963728304 @default.
- W4315704974 hasRelatedWork W1980762553 @default.
- W4315704974 hasRelatedWork W2090756040 @default.
- W4315704974 hasRelatedWork W2094492371 @default.
- W4315704974 hasRelatedWork W2160484851 @default.
- W4315704974 isParatext "false" @default.
- W4315704974 isRetracted "false" @default.
- W4315704974 workType "article" @default.