Matches in SemOpenAlex for { <https://semopenalex.org/work/W2563044023> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2563044023 endingPage "16083" @default.
- W2563044023 startingPage "16077" @default.
- W2563044023 abstract "Long short-term memory (LSTM) has been widely used in different applications, such as natural language processing, speech recognition, and computer vision over recurrent neural network (RNN) or recursive neural network (RvNN)-a tree-structured RNN. In addition, the LSTM-RvNN has been used to represent compositional semantics through the connections of hidden vectors over child units. However, the linear connections in the existing LSTM networks are incapable of capturing complex semantic representations of natural language texts. For example, complex structures in natural language texts usually denote intricate relationships between words, such as negated sentiment or sentiment strengths. In this paper, quadratic connections of the LSTM model is proposed in terms of RvNNs (abbreviated as qLSTM-RvNN) in order to attack the problem of representing compositional semantics. The proposed qLSTM-RvNN model is evaluated in the benchmark data sets containing semantic compositionality, i.e., sentiment analysis on Stanford Sentiment Treebank and semantic relatedness on sentences involving compositional knowledge data set. Empirical results show that it outperforms the state-of-the-art RNN, RvNN, and LSTM networks in two semantic compositionality tasks by increasing the classification accuracies and sentence correlation while significantly decreasing computational complexities." @default.
- W2563044023 created "2017-01-06" @default.
- W2563044023 creator A5048464040 @default.
- W2563044023 creator A5057267422 @default.
- W2563044023 date "2017-01-01" @default.
- W2563044023 modified "2023-10-12" @default.
- W2563044023 title "Long Short-Term Memory With Quadratic Connections in Recursive Neural Networks for Representing Compositional Semantics" @default.
- W2563044023 cites W1531333757 @default.
- W2563044023 cites W1632114991 @default.
- W2563044023 cites W1902237438 @default.
- W2563044023 cites W1984052055 @default.
- W2563044023 cites W2005708641 @default.
- W2563044023 cites W2064675550 @default.
- W2563044023 cites W2079735306 @default.
- W2563044023 cites W2100649405 @default.
- W2563044023 cites W2104518905 @default.
- W2563044023 cites W2107878631 @default.
- W2563044023 cites W2133656308 @default.
- W2563044023 cites W2136848157 @default.
- W2563044023 cites W2143612262 @default.
- W2563044023 cites W2250539671 @default.
- W2563044023 cites W2250861254 @default.
- W2563044023 cites W2960930698 @default.
- W2563044023 cites W2963355447 @default.
- W2563044023 cites W3122775348 @default.
- W2563044023 doi "https://doi.org/10.1109/access.2016.2647384" @default.
- W2563044023 hasPublicationYear "2017" @default.
- W2563044023 type Work @default.
- W2563044023 sameAs 2563044023 @default.
- W2563044023 citedByCount "25" @default.
- W2563044023 countsByYear W25630440232017 @default.
- W2563044023 countsByYear W25630440232018 @default.
- W2563044023 countsByYear W25630440232019 @default.
- W2563044023 countsByYear W25630440232020 @default.
- W2563044023 countsByYear W25630440232021 @default.
- W2563044023 countsByYear W25630440232022 @default.
- W2563044023 crossrefType "journal-article" @default.
- W2563044023 hasAuthorship W2563044023A5048464040 @default.
- W2563044023 hasAuthorship W2563044023A5057267422 @default.
- W2563044023 hasBestOaLocation W25630440231 @default.
- W2563044023 hasConcept C121375916 @default.
- W2563044023 hasConcept C13280743 @default.
- W2563044023 hasConcept C147168706 @default.
- W2563044023 hasConcept C154945302 @default.
- W2563044023 hasConcept C184337299 @default.
- W2563044023 hasConcept C185798385 @default.
- W2563044023 hasConcept C186644900 @default.
- W2563044023 hasConcept C195324797 @default.
- W2563044023 hasConcept C199360897 @default.
- W2563044023 hasConcept C204321447 @default.
- W2563044023 hasConcept C205649164 @default.
- W2563044023 hasConcept C206134035 @default.
- W2563044023 hasConcept C2777530160 @default.
- W2563044023 hasConcept C41008148 @default.
- W2563044023 hasConcept C50644808 @default.
- W2563044023 hasConcept C66402592 @default.
- W2563044023 hasConceptScore W2563044023C121375916 @default.
- W2563044023 hasConceptScore W2563044023C13280743 @default.
- W2563044023 hasConceptScore W2563044023C147168706 @default.
- W2563044023 hasConceptScore W2563044023C154945302 @default.
- W2563044023 hasConceptScore W2563044023C184337299 @default.
- W2563044023 hasConceptScore W2563044023C185798385 @default.
- W2563044023 hasConceptScore W2563044023C186644900 @default.
- W2563044023 hasConceptScore W2563044023C195324797 @default.
- W2563044023 hasConceptScore W2563044023C199360897 @default.
- W2563044023 hasConceptScore W2563044023C204321447 @default.
- W2563044023 hasConceptScore W2563044023C205649164 @default.
- W2563044023 hasConceptScore W2563044023C206134035 @default.
- W2563044023 hasConceptScore W2563044023C2777530160 @default.
- W2563044023 hasConceptScore W2563044023C41008148 @default.
- W2563044023 hasConceptScore W2563044023C50644808 @default.
- W2563044023 hasConceptScore W2563044023C66402592 @default.
- W2563044023 hasFunder F4320321001 @default.
- W2563044023 hasLocation W25630440231 @default.
- W2563044023 hasOpenAccess W2563044023 @default.
- W2563044023 hasPrimaryLocation W25630440231 @default.
- W2563044023 hasRelatedWork W159132833 @default.
- W2563044023 hasRelatedWork W1818857488 @default.
- W2563044023 hasRelatedWork W2005229811 @default.
- W2563044023 hasRelatedWork W2142065989 @default.
- W2563044023 hasRelatedWork W2251939518 @default.
- W2563044023 hasRelatedWork W2294019741 @default.
- W2563044023 hasRelatedWork W2550024871 @default.
- W2563044023 hasRelatedWork W2789919619 @default.
- W2563044023 hasRelatedWork W2963455036 @default.
- W2563044023 hasRelatedWork W2971623275 @default.
- W2563044023 hasVolume "5" @default.
- W2563044023 isParatext "false" @default.
- W2563044023 isRetracted "false" @default.
- W2563044023 magId "2563044023" @default.
- W2563044023 workType "article" @default.