FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2473329891> ?p ?o ?g. }

• W2473329891 abstract "Sequence-to-sequence deep learning has recently emerged as a new paradigm in supervised learning for spoken language understanding. However, most of the previous studies explored this framework for building single domain models for each task, such as slot filling or domain classification, comparing deep learning based approaches with conventional ones like conditional random fields. This paper proposes a holistic multi-domain, multi-task (i.e. slot filling, domain and intent detection) modeling approach to estimate complete semantic frames for all user utterances addressed to a conversational system, demonstrating the distinctive power of deep learning methods, namely bi-directional recurrent neural network (RNN) with long-short term memory (LSTM) cells (RNN-LSTM) to handle such complexity. The contributions of the presented work are three-fold: (i) we propose an RNN-LSTM architecture for joint modeling of slot filling, intent determination, and domain classification; (ii) we build a joint multi-domain model enabling multi-task deep learning where the data from each domain reinforces each other; (iii) we investigate alternative architectures for modeling lexical context in spoken language understanding. In addition to the simplicity of the single model framework, experimental results show the power of such an approach on Microsoft Cortana real user data over alternative methods based on single domain/task deep learning." @default.
• W2473329891 created "2016-07-22" @default.
• W2473329891 creator A5030468199 @default.
• W2473329891 creator A5035017068 @default.
• W2473329891 creator A5047233371 @default.
• W2473329891 creator A5056874223 @default.
• W2473329891 creator A5068709817 @default.
• W2473329891 creator A5076610826 @default.
• W2473329891 creator A5087941479 @default.
• W2473329891 date "2016-09-08" @default.
• W2473329891 modified "2023-10-18" @default.
• W2473329891 title "Multi-Domain Joint Semantic Frame Parsing Using Bi-Directional RNN-LSTM" @default.
• W2473329891 cites W1550863320 @default.
• W2473329891 cites W1591706642 @default.
• W2473329891 cites W1614298861 @default.
• W2473329891 cites W1815076433 @default.
• W2473329891 cites W1948566616 @default.
• W2473329891 cites W1951216520 @default.
• W2473329891 cites W1964812476 @default.
• W2473329891 cites W1971034924 @default.
• W2473329891 cites W2023384780 @default.
• W2473329891 cites W2024632416 @default.
• W2473329891 cites W2053463056 @default.
• W2473329891 cites W2064675550 @default.
• W2473329891 cites W2074818733 @default.
• W2473329891 cites W2091671846 @default.
• W2473329891 cites W2094472029 @default.
• W2473329891 cites W2106347453 @default.
• W2473329891 cites W2107878631 @default.
• W2473329891 cites W2110485445 @default.
• W2473329891 cites W2124895976 @default.
• W2473329891 cites W2129554061 @default.
• W2473329891 cites W2130942839 @default.
• W2473329891 cites W2137871902 @default.
• W2473329891 cites W2146502635 @default.
• W2473329891 cites W2158899491 @default.
• W2473329891 cites W2166293310 @default.
• W2473329891 cites W2170919426 @default.
• W2473329891 cites W2252022287 @default.
• W2473329891 cites W2252070015 @default.
• W2473329891 cites W2395389931 @default.
• W2473329891 cites W2399456070 @default.
• W2473329891 cites W2400801499 @default.
• W2473329891 cites W2405622356 @default.
• W2473329891 cites W2407905223 @default.
• W2473329891 cites W2473965551 @default.
• W2473329891 cites W581956982 @default.
• W2473329891 cites W648947103 @default.
• W2473329891 cites W7628034 @default.
• W2473329891 cites W3023071679 @default.
• W2473329891 doi "https://doi.org/10.21437/interspeech.2016-402" @default.
• W2473329891 hasPublicationYear "2016" @default.
• W2473329891 type Work @default.
• W2473329891 sameAs 2473329891 @default.
• W2473329891 citedByCount "335" @default.
• W2473329891 countsByYear W24733298912016 @default.
• W2473329891 countsByYear W24733298912017 @default.
• W2473329891 countsByYear W24733298912018 @default.
• W2473329891 countsByYear W24733298912019 @default.
• W2473329891 countsByYear W24733298912020 @default.
• W2473329891 countsByYear W24733298912021 @default.
• W2473329891 countsByYear W24733298912022 @default.
• W2473329891 countsByYear W24733298912023 @default.
• W2473329891 crossrefType "proceedings-article" @default.
• W2473329891 hasAuthorship W2473329891A5030468199 @default.
• W2473329891 hasAuthorship W2473329891A5035017068 @default.
• W2473329891 hasAuthorship W2473329891A5047233371 @default.
• W2473329891 hasAuthorship W2473329891A5056874223 @default.
• W2473329891 hasAuthorship W2473329891A5068709817 @default.
• W2473329891 hasAuthorship W2473329891A5076610826 @default.
• W2473329891 hasAuthorship W2473329891A5087941479 @default.
• W2473329891 hasConcept C108583219 @default.
• W2473329891 hasConcept C126042441 @default.
• W2473329891 hasConcept C134306372 @default.
• W2473329891 hasConcept C147168706 @default.
• W2473329891 hasConcept C151730666 @default.
• W2473329891 hasConcept C152565575 @default.
• W2473329891 hasConcept C154945302 @default.
• W2473329891 hasConcept C162324750 @default.
• W2473329891 hasConcept C186644900 @default.
• W2473329891 hasConcept C187736073 @default.
• W2473329891 hasConcept C204321447 @default.
• W2473329891 hasConcept C2779343474 @default.
• W2473329891 hasConcept C2780451532 @default.
• W2473329891 hasConcept C33923547 @default.
• W2473329891 hasConcept C36503486 @default.
• W2473329891 hasConcept C40506919 @default.
• W2473329891 hasConcept C41008148 @default.
• W2473329891 hasConcept C50644808 @default.
• W2473329891 hasConcept C76155785 @default.
• W2473329891 hasConcept C86803240 @default.
• W2473329891 hasConceptScore W2473329891C108583219 @default.
• W2473329891 hasConceptScore W2473329891C126042441 @default.
• W2473329891 hasConceptScore W2473329891C134306372 @default.
• W2473329891 hasConceptScore W2473329891C147168706 @default.
• W2473329891 hasConceptScore W2473329891C151730666 @default.
• W2473329891 hasConceptScore W2473329891C152565575 @default.
• W2473329891 hasConceptScore W2473329891C154945302 @default.
• W2473329891 hasConceptScore W2473329891C162324750 @default.
• W2473329891 hasConceptScore W2473329891C186644900 @default.

• next