Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Saurabh Tiwary"'
Autor:
Daniel Campos, Xia Song, Rosset Corbin Louis, Paul N. Bennett, Nick Craswell, Saurabh Tiwary, Chenyan Xiong
Publikováno v:
WWW
This paper studies a new scenario in conversational search, conversational question suggestion, which leads search engine users to more engaging experiences by suggesting interesting, informative, and useful follow-up questions. We first establish a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::60d91b3d279635d948993f954aa8e6a5
https://doi.org/10.1145/3366423.3380193
https://doi.org/10.1145/3366423.3380193
Publikováno v:
SIGIR
Axiomatic information retrieval (IR) seeks a set of principle properties desirable in IR models. These properties when formally expressed provide guidance in the search for better relevance estimation functions. Neural ranking models typically contai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9106a9c1d6c98a2e5710d94e4dbf6b27
https://doi.org/10.1145/3331184.3331296
https://doi.org/10.1145/3331184.3331296
Publikováno v:
ACL (1)
When a bilingual student learns to solve word problems in math, we expect the student to be able to solve these problem in both languages the student is fluent in, even if the math lessons were only taught in one language. However, current representa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c5f944c53642ca73504ac44847945666
https://doi.org/10.18653/v1/p19-1395
https://doi.org/10.18653/v1/p19-1395
Autor:
Hongfei Zhang, Corby Rosset, Chenyan Xiong, Saurabh Tiwary, Paul N. Bennett, Nick Craswell, Xia Song
This paper presents GEneric iNtent Encoder (GEN Encoder) which learns a distributed representation space for user intent in search. Leveraging large scale user clicks from Bing search logs as weak supervision of user intent, GEN Encoder learns to map
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::851ccdb44c32e861ffe4b568f197a0c0
Publikováno v:
SIGIR
In web search, typically a candidate generation step selects a small set of documents---from collections containing as many as billions of web pages---that are subsequently ranked and pruned before being presented to the user. In Bing, the candidate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0d8c7a4ec751fe2fd878f6daad8394c5
https://doi.org/10.1145/3209978.3210127
https://doi.org/10.1145/3209978.3210127
Publikováno v:
WSDM
Deep neural networks have recently shown promise in the ad-hoc retrieval task. However, such models have often been based on one field of the document, for example considering document title only or document body only. Since in practice documents typ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dda1371ccae9ec71a6bd8b1185450ee9