Matches in SemOpenAlex for { <https://semopenalex.org/work/W2583962582> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W2583962582 abstract "The question retrieval, which aims to find similar questions of a given question, is playing pivotal role in various question answering (QA) systems. This task is quite challenging mainly on three aspects: lexical gap, polysemy and word order. In this paper, we propose a unified framework to simultaneously handle these three problems. We use word combined with corresponding concept information to handle the polysemous problem. The concept embedding and word embedding are learned at the same time from both context-dependent and context-independent view. The lexical gap problem is handled since the semantic information has been encoded into the embedding. Then, we propose to use a high-level feature embedded convolutional semantic model to learn the question embedding by inputting the concept embedding and word embedding without manually labeling training data. The proposed framework nicely represent the hierarchical structures of word information and concept information in sentences with their layer-by-layer composition and pooling. Finally, the framework is trained in a weakly-supervised manner on question answer pairs, which can be directly obtained without manually labeling. Experiments on two real question answering datasets show that the proposed framework can significantly outperform the state-of-the-art solutions." @default.
- W2583962582 created "2017-02-10" @default.
- W2583962582 creator A5007610265 @default.
- W2583962582 creator A5030330619 @default.
- W2583962582 creator A5064222660 @default.
- W2583962582 creator A5075965915 @default.
- W2583962582 creator A5080674767 @default.
- W2583962582 date "2017-02-02" @default.
- W2583962582 modified "2023-09-25" @default.
- W2583962582 title "Concept Embedded Convolutional Semantic Model for Question Retrieval" @default.
- W2583962582 cites W1970875273 @default.
- W2583962582 cites W1986321089 @default.
- W2583962582 cites W1994842363 @default.
- W2583962582 cites W2035363410 @default.
- W2583962582 cites W2048370214 @default.
- W2583962582 cites W2056260421 @default.
- W2583962582 cites W2061298001 @default.
- W2583962582 cites W2131876387 @default.
- W2583962582 cites W2136189984 @default.
- W2583962582 cites W2138605095 @default.
- W2583962582 cites W2147308966 @default.
- W2583962582 cites W2162355876 @default.
- W2583962582 cites W2162456950 @default.
- W2583962582 cites W2165612380 @default.
- W2583962582 cites W2250930514 @default.
- W2583962582 cites W2252143362 @default.
- W2583962582 cites W2997617958 @default.
- W2583962582 cites W2998704965 @default.
- W2583962582 cites W4240913316 @default.
- W2583962582 cites W4251560691 @default.
- W2583962582 doi "https://doi.org/10.1145/3018661.3018687" @default.
- W2583962582 hasPublicationYear "2017" @default.
- W2583962582 type Work @default.
- W2583962582 sameAs 2583962582 @default.
- W2583962582 citedByCount "6" @default.
- W2583962582 countsByYear W25839625822018 @default.
- W2583962582 countsByYear W25839625822019 @default.
- W2583962582 countsByYear W25839625822020 @default.
- W2583962582 crossrefType "proceedings-article" @default.
- W2583962582 hasAuthorship W2583962582A5007610265 @default.
- W2583962582 hasAuthorship W2583962582A5030330619 @default.
- W2583962582 hasAuthorship W2583962582A5064222660 @default.
- W2583962582 hasAuthorship W2583962582A5075965915 @default.
- W2583962582 hasAuthorship W2583962582A5080674767 @default.
- W2583962582 hasConcept C154945302 @default.
- W2583962582 hasConcept C204321447 @default.
- W2583962582 hasConcept C23123220 @default.
- W2583962582 hasConcept C41008148 @default.
- W2583962582 hasConcept C81363708 @default.
- W2583962582 hasConceptScore W2583962582C154945302 @default.
- W2583962582 hasConceptScore W2583962582C204321447 @default.
- W2583962582 hasConceptScore W2583962582C23123220 @default.
- W2583962582 hasConceptScore W2583962582C41008148 @default.
- W2583962582 hasConceptScore W2583962582C81363708 @default.
- W2583962582 hasLocation W25839625821 @default.
- W2583962582 hasOpenAccess W2583962582 @default.
- W2583962582 hasPrimaryLocation W25839625821 @default.
- W2583962582 hasRelatedWork W2384888906 @default.
- W2583962582 hasRelatedWork W2521062615 @default.
- W2583962582 hasRelatedWork W2735477435 @default.
- W2583962582 hasRelatedWork W2749468216 @default.
- W2583962582 hasRelatedWork W2901465038 @default.
- W2583962582 hasRelatedWork W2998526951 @default.
- W2583962582 hasRelatedWork W3090822330 @default.
- W2583962582 hasRelatedWork W3107474891 @default.
- W2583962582 hasRelatedWork W3119610945 @default.
- W2583962582 hasRelatedWork W3181746755 @default.
- W2583962582 isParatext "false" @default.
- W2583962582 isRetracted "false" @default.
- W2583962582 magId "2583962582" @default.
- W2583962582 workType "article" @default.