Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003611599> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3003611599 abstract "Search queries are often short, and the underlying user intent may be ambiguous. This makes it challenging for search engines to predict possible intents, only one of which may pertain to the current user. To address this issue, search engines often diversify the result list and present documents relevant to multiple intents of the query. An alternative approach is to ask the user a question to clarify her information need. Asking clarifying questions is particularly important for scenarios with “limited bandwidth” interfaces, such as speech-only and small-screen devices. In addition, our user studies and large-scale online experiments show that asking clarifying questions is also useful in web search. Although some recent studies have pointed out the importance of asking clarifying questions, generating them for open-domain search tasks remains unstudied and is the focus of this paper. Lack of training data even within major search engines for this task makes it challenging. To mitigate this issue, we first identify a taxonomy of clarification for open-domain search queries by analyzing large-scale query reformulation data sampled from Bing search logs. This taxonomy leads us to a set of question templates and a simple yet effective slot filling algorithm. We further use this model as a source of weak supervision to automatically generate clarifying questions for training. Furthermore, we propose supervised and reinforcement learning models for generating clarifying questions learned from weak supervision data. We also investigate methods for generating candidate answers for each clarifying question, so users can select from a set of pre-defined answers. Human evaluation of the clarifying questions and candidate answers for hundreds of search queries demonstrates the effectiveness of the proposed solutions." @default.
- W3003611599 created "2020-02-07" @default.
- W3003611599 creator A5008885979 @default.
- W3003611599 creator A5017350695 @default.
- W3003611599 creator A5026109848 @default.
- W3003611599 creator A5055132321 @default.
- W3003611599 creator A5058953933 @default.
- W3003611599 date "2020-04-19" @default.
- W3003611599 modified "2023-10-11" @default.
- W3003611599 title "Generating Clarifying Questions for Information Retrieval" @default.
- W3003611599 cites W1493399377 @default.
- W3003611599 cites W1530635668 @default.
- W3003611599 cites W1546599055 @default.
- W3003611599 cites W2018838261 @default.
- W3003611599 cites W2025201259 @default.
- W3003611599 cites W2098019918 @default.
- W3003611599 cites W2117079628 @default.
- W3003611599 cites W2119717200 @default.
- W3003611599 cites W2131774270 @default.
- W3003611599 cites W2143017621 @default.
- W3003611599 cites W2143697166 @default.
- W3003611599 cites W2158848165 @default.
- W3003611599 cites W2170443290 @default.
- W3003611599 cites W2171784453 @default.
- W3003611599 cites W2247275455 @default.
- W3003611599 cites W2250539671 @default.
- W3003611599 cites W2257117461 @default.
- W3003611599 cites W2410226802 @default.
- W3003611599 cites W2510769428 @default.
- W3003611599 cites W2522306626 @default.
- W3003611599 cites W2590822507 @default.
- W3003611599 cites W2593527188 @default.
- W3003611599 cites W2606333299 @default.
- W3003611599 cites W2755600468 @default.
- W3003611599 cites W2757978590 @default.
- W3003611599 cites W2798575418 @default.
- W3003611599 cites W2798631888 @default.
- W3003611599 cites W2809897079 @default.
- W3003611599 cites W2889742741 @default.
- W3003611599 cites W2889757348 @default.
- W3003611599 cites W2897754576 @default.
- W3003611599 cites W2963033005 @default.
- W3003611599 cites W3101380159 @default.
- W3003611599 cites W3105690102 @default.
- W3003611599 cites W3138773240 @default.
- W3003611599 cites W4206671592 @default.
- W3003611599 doi "https://doi.org/10.1145/3366423.3380126" @default.
- W3003611599 hasPublicationYear "2020" @default.
- W3003611599 type Work @default.
- W3003611599 sameAs 3003611599 @default.
- W3003611599 citedByCount "99" @default.
- W3003611599 countsByYear W30036115992019 @default.
- W3003611599 countsByYear W30036115992020 @default.
- W3003611599 countsByYear W30036115992021 @default.
- W3003611599 countsByYear W30036115992022 @default.
- W3003611599 countsByYear W30036115992023 @default.
- W3003611599 crossrefType "proceedings-article" @default.
- W3003611599 hasAuthorship W3003611599A5008885979 @default.
- W3003611599 hasAuthorship W3003611599A5017350695 @default.
- W3003611599 hasAuthorship W3003611599A5026109848 @default.
- W3003611599 hasAuthorship W3003611599A5055132321 @default.
- W3003611599 hasAuthorship W3003611599A5058953933 @default.
- W3003611599 hasConcept C23123220 @default.
- W3003611599 hasConcept C41008148 @default.
- W3003611599 hasConceptScore W3003611599C23123220 @default.
- W3003611599 hasConceptScore W3003611599C41008148 @default.
- W3003611599 hasLocation W30036115991 @default.
- W3003611599 hasOpenAccess W3003611599 @default.
- W3003611599 hasPrimaryLocation W30036115991 @default.
- W3003611599 hasRelatedWork W2101955803 @default.
- W3003611599 hasRelatedWork W2115485936 @default.
- W3003611599 hasRelatedWork W2119135658 @default.
- W3003611599 hasRelatedWork W2119214692 @default.
- W3003611599 hasRelatedWork W2144190808 @default.
- W3003611599 hasRelatedWork W2357241418 @default.
- W3003611599 hasRelatedWork W2366644548 @default.
- W3003611599 hasRelatedWork W2376314740 @default.
- W3003611599 hasRelatedWork W2384888906 @default.
- W3003611599 hasRelatedWork W2469626427 @default.
- W3003611599 isParatext "false" @default.
- W3003611599 isRetracted "false" @default.
- W3003611599 magId "3003611599" @default.
- W3003611599 workType "article" @default.