Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128459263> ?p ?o ?g. }
- W3128459263 abstract "Uncertainty estimation is important for ensuring safety and robustness of AI systems. While most research in the area has focused on un-structured prediction tasks, limited work has investigated general uncertainty estimation approaches for structured prediction. Thus, this work aims to investigate uncertainty estimation for autoregressive structured prediction tasks within a single unified and interpretable probabilistic ensemble-based framework. We consider: uncertainty estimation for sequence data at the token-level and complete sequence-level; interpretations for, and applications of, various measures of uncertainty; and discuss both the theoretical and practical challenges associated with obtaining them. This work also provides baselines for token-level and sequence-level error detection, and sequence-level out-of-domain input detection on the WMT'14 English-French and WMT'17 English-German translation and LibriSpeech speech recognition datasets." @default.
- W3128459263 created "2021-02-15" @default.
- W3128459263 creator A5050766679 @default.
- W3128459263 creator A5080001860 @default.
- W3128459263 date "2020-02-18" @default.
- W3128459263 modified "2023-09-27" @default.
- W3128459263 title "Uncertainty Estimation in Autoregressive Structured Prediction" @default.
- W3128459263 cites W1494198834 @default.
- W3128459263 cites W1569447338 @default.
- W3128459263 cites W179875071 @default.
- W3128459263 cites W1855892484 @default.
- W3128459263 cites W1916559533 @default.
- W3128459263 cites W2099111195 @default.
- W3128459263 cites W2111093880 @default.
- W3128459263 cites W2127141656 @default.
- W3128459263 cites W2129334286 @default.
- W3128459263 cites W2141599568 @default.
- W3128459263 cites W2142416747 @default.
- W3128459263 cites W2184045248 @default.
- W3128459263 cites W2462906003 @default.
- W3128459263 cites W2531327146 @default.
- W3128459263 cites W2591949110 @default.
- W3128459263 cites W2607738331 @default.
- W3128459263 cites W2739575494 @default.
- W3128459263 cites W2765867474 @default.
- W3128459263 cites W2767206889 @default.
- W3128459263 cites W2790319220 @default.
- W3128459263 cites W2806311723 @default.
- W3128459263 cites W2898630520 @default.
- W3128459263 cites W2912168444 @default.
- W3128459263 cites W2918914336 @default.
- W3128459263 cites W2933138175 @default.
- W3128459263 cites W2938704169 @default.
- W3128459263 cites W2941814890 @default.
- W3128459263 cites W2947433239 @default.
- W3128459263 cites W2950577311 @default.
- W3128459263 cites W2962784628 @default.
- W3128459263 cites W2962835968 @default.
- W3128459263 cites W2963238274 @default.
- W3128459263 cites W2963403868 @default.
- W3128459263 cites W2963532001 @default.
- W3128459263 cites W2963564844 @default.
- W3128459263 cites W2964059111 @default.
- W3128459263 cites W2964308564 @default.
- W3128459263 cites W2964317943 @default.
- W3128459263 cites W2970693987 @default.
- W3128459263 cites W2970859221 @default.
- W3128459263 cites W2971570684 @default.
- W3128459263 cites W2992525328 @default.
- W3128459263 cites W2995464762 @default.
- W3128459263 cites W2995929068 @default.
- W3128459263 cites W2996184071 @default.
- W3128459263 cites W3003199999 @default.
- W3128459263 cites W3084095723 @default.
- W3128459263 cites W3118026775 @default.
- W3128459263 hasPublicationYear "2020" @default.
- W3128459263 type Work @default.
- W3128459263 sameAs 3128459263 @default.
- W3128459263 citedByCount "2" @default.
- W3128459263 countsByYear W31284592632020 @default.
- W3128459263 countsByYear W31284592632021 @default.
- W3128459263 crossrefType "posted-content" @default.
- W3128459263 hasAuthorship W3128459263A5050766679 @default.
- W3128459263 hasAuthorship W3128459263A5080001860 @default.
- W3128459263 hasConcept C104317684 @default.
- W3128459263 hasConcept C119857082 @default.
- W3128459263 hasConcept C124101348 @default.
- W3128459263 hasConcept C149782125 @default.
- W3128459263 hasConcept C154945302 @default.
- W3128459263 hasConcept C159877910 @default.
- W3128459263 hasConcept C162324750 @default.
- W3128459263 hasConcept C185592680 @default.
- W3128459263 hasConcept C187736073 @default.
- W3128459263 hasConcept C2778112365 @default.
- W3128459263 hasConcept C33923547 @default.
- W3128459263 hasConcept C38652104 @default.
- W3128459263 hasConcept C41008148 @default.
- W3128459263 hasConcept C48145219 @default.
- W3128459263 hasConcept C49937458 @default.
- W3128459263 hasConcept C54355233 @default.
- W3128459263 hasConcept C55493867 @default.
- W3128459263 hasConcept C63479239 @default.
- W3128459263 hasConcept C86803240 @default.
- W3128459263 hasConcept C96250715 @default.
- W3128459263 hasConceptScore W3128459263C104317684 @default.
- W3128459263 hasConceptScore W3128459263C119857082 @default.
- W3128459263 hasConceptScore W3128459263C124101348 @default.
- W3128459263 hasConceptScore W3128459263C149782125 @default.
- W3128459263 hasConceptScore W3128459263C154945302 @default.
- W3128459263 hasConceptScore W3128459263C159877910 @default.
- W3128459263 hasConceptScore W3128459263C162324750 @default.
- W3128459263 hasConceptScore W3128459263C185592680 @default.
- W3128459263 hasConceptScore W3128459263C187736073 @default.
- W3128459263 hasConceptScore W3128459263C2778112365 @default.
- W3128459263 hasConceptScore W3128459263C33923547 @default.
- W3128459263 hasConceptScore W3128459263C38652104 @default.
- W3128459263 hasConceptScore W3128459263C41008148 @default.
- W3128459263 hasConceptScore W3128459263C48145219 @default.
- W3128459263 hasConceptScore W3128459263C49937458 @default.
- W3128459263 hasConceptScore W3128459263C54355233 @default.