Matches in SemOpenAlex for { <https://semopenalex.org/work/W2610935556> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2610935556 abstract "Despite the impressive improvements achieved by unsupervised deep neural networks in computer vision and NLP tasks, such improvements have not yet been observed in ranking for information retrieval. The reason may be the complexity of the ranking problem, as it is not obvious how to learn from queries and documents when no supervised signal is available. Hence, in this paper, we propose to train a neural ranking model using weak supervision, where labels are obtained automatically without human annotators or any external resources (e.g., click data). To this aim, we use the output of an unsupervised ranking model, such as BM25, as a weak supervision signal. We further train a set of simple yet effective ranking models based on feed-forward neural networks. We study their effectiveness under various learning scenarios (point-wise and pair-wise models) and using different input representations (i.e., from encoding query-document pairs into dense/sparse vectors to using word embedding representation). We train our networks using tens of millions of training instances and evaluate it on two standard collections: a homogeneous news collection (Robust) and a heterogeneous large-scale web collection (ClueWeb). Our experiments indicate that employing proper objective functions and letting the networks to learn the input representation based on weakly supervised data leads to impressive performance, with over 13% and 35% MAP improvements over the BM25 model on the Robust and the ClueWeb collections. Our findings also suggest that supervised neural ranking models can greatly benefit from pre-training on large amounts of weakly labeled data that can be easily obtained from unsupervised IR models." @default.
- W2610935556 created "2017-05-12" @default.
- W2610935556 creator A5008885979 @default.
- W2610935556 creator A5031888985 @default.
- W2610935556 creator A5044511901 @default.
- W2610935556 creator A5047094005 @default.
- W2610935556 creator A5080125160 @default.
- W2610935556 date "2017-08-07" @default.
- W2610935556 modified "2023-10-15" @default.
- W2610935556 title "Neural Ranking Models with Weak Supervision" @default.
- W2610935556 cites W1685426458 @default.
- W2610935556 cites W2047221353 @default.
- W2610935556 cites W2058475745 @default.
- W2610935556 cites W2069870183 @default.
- W2610935556 cites W2250539671 @default.
- W2610935556 cites W2295072214 @default.
- W2610935556 cites W2336930964 @default.
- W2610935556 cites W2339829457 @default.
- W2610935556 cites W2510769428 @default.
- W2610935556 cites W2515174656 @default.
- W2610935556 cites W2515351093 @default.
- W2610935556 cites W2515565210 @default.
- W2610935556 cites W2538374209 @default.
- W2610935556 cites W2539671052 @default.
- W2610935556 cites W2616619952 @default.
- W2610935556 cites W2919115771 @default.
- W2610935556 cites W2997183031 @default.
- W2610935556 cites W3099984837 @default.
- W2610935556 doi "https://doi.org/10.1145/3077136.3080832" @default.
- W2610935556 hasPublicationYear "2017" @default.
- W2610935556 type Work @default.
- W2610935556 sameAs 2610935556 @default.
- W2610935556 citedByCount "249" @default.
- W2610935556 countsByYear W26109355562017 @default.
- W2610935556 countsByYear W26109355562018 @default.
- W2610935556 countsByYear W26109355562019 @default.
- W2610935556 countsByYear W26109355562020 @default.
- W2610935556 countsByYear W26109355562021 @default.
- W2610935556 countsByYear W26109355562022 @default.
- W2610935556 countsByYear W26109355562023 @default.
- W2610935556 crossrefType "proceedings-article" @default.
- W2610935556 hasAuthorship W2610935556A5008885979 @default.
- W2610935556 hasAuthorship W2610935556A5031888985 @default.
- W2610935556 hasAuthorship W2610935556A5044511901 @default.
- W2610935556 hasAuthorship W2610935556A5047094005 @default.
- W2610935556 hasAuthorship W2610935556A5080125160 @default.
- W2610935556 hasBestOaLocation W26109355561 @default.
- W2610935556 hasConcept C119857082 @default.
- W2610935556 hasConcept C154945302 @default.
- W2610935556 hasConcept C177264268 @default.
- W2610935556 hasConcept C17744445 @default.
- W2610935556 hasConcept C189430467 @default.
- W2610935556 hasConcept C199360897 @default.
- W2610935556 hasConcept C199539241 @default.
- W2610935556 hasConcept C23123220 @default.
- W2610935556 hasConcept C2524010 @default.
- W2610935556 hasConcept C2776359362 @default.
- W2610935556 hasConcept C28719098 @default.
- W2610935556 hasConcept C33923547 @default.
- W2610935556 hasConcept C41008148 @default.
- W2610935556 hasConcept C50644808 @default.
- W2610935556 hasConcept C86037889 @default.
- W2610935556 hasConcept C94625758 @default.
- W2610935556 hasConceptScore W2610935556C119857082 @default.
- W2610935556 hasConceptScore W2610935556C154945302 @default.
- W2610935556 hasConceptScore W2610935556C177264268 @default.
- W2610935556 hasConceptScore W2610935556C17744445 @default.
- W2610935556 hasConceptScore W2610935556C189430467 @default.
- W2610935556 hasConceptScore W2610935556C199360897 @default.
- W2610935556 hasConceptScore W2610935556C199539241 @default.
- W2610935556 hasConceptScore W2610935556C23123220 @default.
- W2610935556 hasConceptScore W2610935556C2524010 @default.
- W2610935556 hasConceptScore W2610935556C2776359362 @default.
- W2610935556 hasConceptScore W2610935556C28719098 @default.
- W2610935556 hasConceptScore W2610935556C33923547 @default.
- W2610935556 hasConceptScore W2610935556C41008148 @default.
- W2610935556 hasConceptScore W2610935556C50644808 @default.
- W2610935556 hasConceptScore W2610935556C86037889 @default.
- W2610935556 hasConceptScore W2610935556C94625758 @default.
- W2610935556 hasFunder F4320321800 @default.
- W2610935556 hasLocation W26109355561 @default.
- W2610935556 hasLocation W26109355562 @default.
- W2610935556 hasOpenAccess W2610935556 @default.
- W2610935556 hasPrimaryLocation W26109355561 @default.
- W2610935556 hasRelatedWork W2138488530 @default.
- W2610935556 hasRelatedWork W2385796165 @default.
- W2610935556 hasRelatedWork W2387658907 @default.
- W2610935556 hasRelatedWork W25098770 @default.
- W2610935556 hasRelatedWork W2798835721 @default.
- W2610935556 hasRelatedWork W2898073868 @default.
- W2610935556 hasRelatedWork W2922169395 @default.
- W2610935556 hasRelatedWork W2971071571 @default.
- W2610935556 hasRelatedWork W3127142483 @default.
- W2610935556 hasRelatedWork W4385565564 @default.
- W2610935556 isParatext "false" @default.
- W2610935556 isRetracted "false" @default.
- W2610935556 magId "2610935556" @default.
- W2610935556 workType "article" @default.