FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3031058832> ?p ?o ?g. }

• W3031058832 startingPage "20" @default.
• W3031058832 abstract "In this paper, we tackle the problem of lack of understandability of deep learning systems by integrating heterogeneous knowledge sources, and in the specific we present how we used FrameNet to guarantee the correct learning for an LSTM-based semantic parser in the task of Spoken Language Understanding for robots. The problem of the explainability of Artificial Intelligence (AI) systems, i.e. their ability to explain decisions to both experts and end users, has attracted growing attention in the latest years, affecting their credibility and trustworthiness. Trusting these systems is fundamental in the context of AI-based robotic companions interacting in natural language, as the users’ acceptance of the robot also relies on the ability to explain the reasons behind its actions. Following similar approaches, we first use the values of the neural attention layers employed in the semantic parser as a clue to analyze and interpret the model’s behavior and reveal the intrinsic bias induced by the training data. We then show how the integration of knowledge from external resources such as FrameNet can help minimizing, or mitigating, such bias, and consequently guarantee the model to provide the correct interpretations. Our preliminary, but promising results suggest that (i) attention layers can improve the model understandability; (ii) the integration of different knowledge bases can help overcoming the limitations of machine learning models; and (iii) an approach combining the strengths of both knowledge engineering and machine learning can foster the development of more transparent, understandable intelligent systems." @default.
• W3031058832 created "2020-06-05" @default.
• W3031058832 creator A5039390267 @default.
• W3031058832 creator A5075467369 @default.
• W3031058832 creator A5088281457 @default.
• W3031058832 creator A5088463134 @default.
• W3031058832 date "2020-05-05" @default.
• W3031058832 modified "2023-09-24" @default.
• W3031058832 title "Mitigating bias in deep nets with knowledge bases : The case of natural language understanding for robots" @default.
• W3031058832 cites W1485735559 @default.
• W3031058832 cites W1528951054 @default.
• W3031058832 cites W1569430537 @default.
• W3031058832 cites W1745379580 @default.
• W3031058832 cites W1849277567 @default.
• W3031058832 cites W1949907236 @default.
• W3031058832 cites W2069809153 @default.
• W3031058832 cites W2110609845 @default.
• W3031058832 cites W2115792525 @default.
• W3031058832 cites W2118781169 @default.
• W3031058832 cites W2133564696 @default.
• W3031058832 cites W2138455848 @default.
• W3031058832 cites W2189089430 @default.
• W3031058832 cites W2250539671 @default.
• W3031058832 cites W2270642299 @default.
• W3031058832 cites W2282821441 @default.
• W3031058832 cites W2293350124 @default.
• W3031058832 cites W2550442559 @default.
• W3031058832 cites W2589644515 @default.
• W3031058832 cites W2805885300 @default.
• W3031058832 cites W2900907103 @default.
• W3031058832 cites W2900975567 @default.
• W3031058832 cites W2949615363 @default.
• W3031058832 cites W2950178297 @default.
• W3031058832 cites W2951527505 @default.
• W3031058832 cites W2953022248 @default.
• W3031058832 cites W2962851944 @default.
• W3031058832 cites W2963374347 @default.
• W3031058832 cites W2963974889 @default.
• W3031058832 cites W2979669231 @default.
• W3031058832 hasPublicationYear "2020" @default.
• W3031058832 type Work @default.
• W3031058832 sameAs 3031058832 @default.
• W3031058832 citedByCount "0" @default.
• W3031058832 crossrefType "proceedings-article" @default.
• W3031058832 hasAuthorship W3031058832A5039390267 @default.
• W3031058832 hasAuthorship W3031058832A5075467369 @default.
• W3031058832 hasAuthorship W3031058832A5088281457 @default.
• W3031058832 hasAuthorship W3031058832A5088463134 @default.
• W3031058832 hasConcept C107457646 @default.
• W3031058832 hasConcept C151730666 @default.
• W3031058832 hasConcept C154945302 @default.
• W3031058832 hasConcept C162324750 @default.
• W3031058832 hasConcept C17744445 @default.
• W3031058832 hasConcept C185754541 @default.
• W3031058832 hasConcept C186644900 @default.
• W3031058832 hasConcept C187736073 @default.
• W3031058832 hasConcept C195324797 @default.
• W3031058832 hasConcept C199539241 @default.
• W3031058832 hasConcept C204321447 @default.
• W3031058832 hasConcept C2779343474 @default.
• W3031058832 hasConcept C2779439875 @default.
• W3031058832 hasConcept C2780224610 @default.
• W3031058832 hasConcept C2780451532 @default.
• W3031058832 hasConcept C41008148 @default.
• W3031058832 hasConcept C86803240 @default.
• W3031058832 hasConcept C90509273 @default.
• W3031058832 hasConceptScore W3031058832C107457646 @default.
• W3031058832 hasConceptScore W3031058832C151730666 @default.
• W3031058832 hasConceptScore W3031058832C154945302 @default.
• W3031058832 hasConceptScore W3031058832C162324750 @default.
• W3031058832 hasConceptScore W3031058832C17744445 @default.
• W3031058832 hasConceptScore W3031058832C185754541 @default.
• W3031058832 hasConceptScore W3031058832C186644900 @default.
• W3031058832 hasConceptScore W3031058832C187736073 @default.
• W3031058832 hasConceptScore W3031058832C195324797 @default.
• W3031058832 hasConceptScore W3031058832C199539241 @default.
• W3031058832 hasConceptScore W3031058832C204321447 @default.
• W3031058832 hasConceptScore W3031058832C2779343474 @default.
• W3031058832 hasConceptScore W3031058832C2779439875 @default.
• W3031058832 hasConceptScore W3031058832C2780224610 @default.
• W3031058832 hasConceptScore W3031058832C2780451532 @default.
• W3031058832 hasConceptScore W3031058832C41008148 @default.
• W3031058832 hasConceptScore W3031058832C86803240 @default.
• W3031058832 hasConceptScore W3031058832C90509273 @default.
• W3031058832 hasLocation W30310588321 @default.
• W3031058832 hasOpenAccess W3031058832 @default.
• W3031058832 hasPrimaryLocation W30310588321 @default.
• W3031058832 hasRelatedWork W1493353544 @default.
• W3031058832 hasRelatedWork W1597539752 @default.
• W3031058832 hasRelatedWork W1984328371 @default.
• W3031058832 hasRelatedWork W2181506300 @default.
• W3031058832 hasRelatedWork W2469652855 @default.
• W3031058832 hasRelatedWork W2573749176 @default.
• W3031058832 hasRelatedWork W2766569996 @default.
• W3031058832 hasRelatedWork W277406721 @default.
• W3031058832 hasRelatedWork W2896106928 @default.
• W3031058832 hasRelatedWork W3001825839 @default.
• W3031058832 hasRelatedWork W3008128620 @default.
• W3031058832 hasRelatedWork W3013757419 @default.

• next