Matches in SemOpenAlex for { <https://semopenalex.org/work/W3099202331> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3099202331 endingPage "168" @default.
- W3099202331 startingPage "147" @default.
- W3099202331 abstract "VT (Viterbi training), or hard EM, is an efficient way of parameter learning for probabilistic models with hidden variables. Given an observation $y$, it searches for a state of hidden variables $x$ that maximizes $p(x,y mid theta)$ by coordinate ascent on parameters $theta$ and $x$. In this paper we introduce VT to PRISM, a logic-based probabilistic modeling system for generative models. VT improves PRISM in three ways. First VT in PRISM converges faster than EM in PRISM due to the VT's termination condition. Second, parameters learned by VT often show good prediction performance compared to those learned by EM. We conducted two parsing experiments with probabilistic grammars while learning parameters by a variety of inference methods, i.e. VT, EM, MAP and VB. The result is that VT achieved the best parsing accuracy among them in both experiments. Also we conducted a similar experiment for classification tasks where a hidden variable is not a prediction target unlike probabilistic grammars. We found that in such a case VT does not necessarily yield superior performance. Third since VT always deals with a single probability of a single explanation, Viterbi explanation, the exclusiveness condition that is imposed on PRISM programs is no more required if we learn parameters by VT. Last but not least we can say that as VT in PRISM is general and applicable to any PRISM program, it largely reduces the need for the user to develop a specific VT algorithm for a specific model. Furthermore since VT in PRISM can be used just by setting a PRISM flag appropriately, it makes VT easily accessible to (probabilistic) logic programmers. To appear in Theory and Practice of Logic Programming (TPLP)." @default.
- W3099202331 created "2020-11-23" @default.
- W3099202331 creator A5019997517 @default.
- W3099202331 creator A5029285970 @default.
- W3099202331 date "2014-01-28" @default.
- W3099202331 modified "2023-09-24" @default.
- W3099202331 title "Viterbi training in PRISM" @default.
- W3099202331 cites W1215345351 @default.
- W3099202331 cites W1518043585 @default.
- W3099202331 cites W1560531798 @default.
- W3099202331 cites W1585529040 @default.
- W3099202331 cites W1817561967 @default.
- W3099202331 cites W1976019979 @default.
- W3099202331 cites W1983128223 @default.
- W3099202331 cites W2016813284 @default.
- W3099202331 cites W2091346145 @default.
- W3099202331 cites W2093425039 @default.
- W3099202331 cites W2100145144 @default.
- W3099202331 cites W2101335378 @default.
- W3099202331 cites W2110155683 @default.
- W3099202331 cites W2111574971 @default.
- W3099202331 cites W2120283843 @default.
- W3099202331 cites W2123884736 @default.
- W3099202331 cites W2151120711 @default.
- W3099202331 cites W2161562001 @default.
- W3099202331 cites W2164732909 @default.
- W3099202331 cites W2172238468 @default.
- W3099202331 cites W4245055982 @default.
- W3099202331 cites W4255373292 @default.
- W3099202331 doi "https://doi.org/10.1017/s1471068413000677" @default.
- W3099202331 hasPublicationYear "2014" @default.
- W3099202331 type Work @default.
- W3099202331 sameAs 3099202331 @default.
- W3099202331 citedByCount "6" @default.
- W3099202331 countsByYear W30992023312015 @default.
- W3099202331 countsByYear W30992023312016 @default.
- W3099202331 countsByYear W30992023312017 @default.
- W3099202331 countsByYear W30992023312018 @default.
- W3099202331 countsByYear W30992023312021 @default.
- W3099202331 crossrefType "journal-article" @default.
- W3099202331 hasAuthorship W3099202331A5019997517 @default.
- W3099202331 hasAuthorship W3099202331A5029285970 @default.
- W3099202331 hasBestOaLocation W30992023312 @default.
- W3099202331 hasConcept C11413529 @default.
- W3099202331 hasConcept C119857082 @default.
- W3099202331 hasConcept C120665830 @default.
- W3099202331 hasConcept C121332964 @default.
- W3099202331 hasConcept C153180895 @default.
- W3099202331 hasConcept C154945302 @default.
- W3099202331 hasConcept C186644900 @default.
- W3099202331 hasConcept C23224414 @default.
- W3099202331 hasConcept C2776214188 @default.
- W3099202331 hasConcept C28490314 @default.
- W3099202331 hasConcept C41008148 @default.
- W3099202331 hasConcept C49937458 @default.
- W3099202331 hasConcept C53893814 @default.
- W3099202331 hasConcept C60582962 @default.
- W3099202331 hasConcept C67666897 @default.
- W3099202331 hasConceptScore W3099202331C11413529 @default.
- W3099202331 hasConceptScore W3099202331C119857082 @default.
- W3099202331 hasConceptScore W3099202331C120665830 @default.
- W3099202331 hasConceptScore W3099202331C121332964 @default.
- W3099202331 hasConceptScore W3099202331C153180895 @default.
- W3099202331 hasConceptScore W3099202331C154945302 @default.
- W3099202331 hasConceptScore W3099202331C186644900 @default.
- W3099202331 hasConceptScore W3099202331C23224414 @default.
- W3099202331 hasConceptScore W3099202331C2776214188 @default.
- W3099202331 hasConceptScore W3099202331C28490314 @default.
- W3099202331 hasConceptScore W3099202331C41008148 @default.
- W3099202331 hasConceptScore W3099202331C49937458 @default.
- W3099202331 hasConceptScore W3099202331C53893814 @default.
- W3099202331 hasConceptScore W3099202331C60582962 @default.
- W3099202331 hasConceptScore W3099202331C67666897 @default.
- W3099202331 hasIssue "2" @default.
- W3099202331 hasLocation W30992023311 @default.
- W3099202331 hasLocation W30992023312 @default.
- W3099202331 hasOpenAccess W3099202331 @default.
- W3099202331 hasPrimaryLocation W30992023311 @default.
- W3099202331 hasRelatedWork W1505908888 @default.
- W3099202331 hasRelatedWork W1809152426 @default.
- W3099202331 hasRelatedWork W2100982643 @default.
- W3099202331 hasRelatedWork W2107432317 @default.
- W3099202331 hasRelatedWork W2131513205 @default.
- W3099202331 hasRelatedWork W2146661721 @default.
- W3099202331 hasRelatedWork W2347709441 @default.
- W3099202331 hasRelatedWork W2401728283 @default.
- W3099202331 hasRelatedWork W2543733415 @default.
- W3099202331 hasRelatedWork W3099202331 @default.
- W3099202331 hasVolume "15" @default.
- W3099202331 isParatext "false" @default.
- W3099202331 isRetracted "false" @default.
- W3099202331 magId "3099202331" @default.
- W3099202331 workType "article" @default.