Matches in SemOpenAlex for { <https://semopenalex.org/work/W2251937247> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W2251937247 endingPage "10" @default.
- W2251937247 startingPage "9" @default.
- W2251937247 abstract "Historically, key breakthroughs in structured NLP models, such as chain CRFs or PCFGs, have relied on imposing careful constraints on the locality of features in order to permit efficient dynamic programming for computing expectations or finding the highest-scoring structures. However, as modern structured models become more complex and seek to incorporate longer-range features, it is more and more often the case that performing exact inference is impossible (or at least impractical) and it is necessary to resort to some sort of approximation technique, such as beam search, pruning, or sampling. In the NLP community, one increasingly popular approach is the use of variational methods for computing approximate distributions. The goal of the tutorial is to provide an introduction to variational methods for approximate inference, particularly mean field approximation and belief propagation. The intuition behind the mathematical derivation of variational methods is fairly simple: instead of trying to directly compute the distribution of interest, first consider some efficiently computable approximation of the original inference problem, then find the solution of the approximate inference problem that minimizes the distance to the true distribution. Though the full derivations can be somewhat tedious, the resulting procedures are quite straightforward, and typically consist of an iterative process of individually updating specific components of the model, conditioned on the rest. Although we will provide some theoretical background, the main goal of the tutorial is to provide a concrete procedural guide to using these approximate inference techniques, illustrated with detailed walkthroughs of examples from recent NLP literature. Once both variational inference procedures have been described in detail, we’ll provide a summary comparison of the two, along with some intuition about which approach is appropriate when. We’ll also provide a guide to further exploration of the topic, briefly discussing other variational techniques, such as expectation propagation and convex relaxations, but concentrating mainly on providing pointers to additional resources for those who wish to learn more." @default.
- W2251937247 created "2016-06-24" @default.
- W2251937247 creator A5003197445 @default.
- W2251937247 creator A5004921249 @default.
- W2251937247 date "2013-08-01" @default.
- W2251937247 modified "2023-09-23" @default.
- W2251937247 title "Variational Inference for Structured NLP Models" @default.
- W2251937247 hasPublicationYear "2013" @default.
- W2251937247 type Work @default.
- W2251937247 sameAs 2251937247 @default.
- W2251937247 citedByCount "0" @default.
- W2251937247 crossrefType "proceedings-article" @default.
- W2251937247 hasAuthorship W2251937247A5003197445 @default.
- W2251937247 hasAuthorship W2251937247A5004921249 @default.
- W2251937247 hasConcept C108010975 @default.
- W2251937247 hasConcept C11413529 @default.
- W2251937247 hasConcept C119857082 @default.
- W2251937247 hasConcept C138885662 @default.
- W2251937247 hasConcept C154945302 @default.
- W2251937247 hasConcept C2776214188 @default.
- W2251937247 hasConcept C2777472644 @default.
- W2251937247 hasConcept C2779808786 @default.
- W2251937247 hasConcept C41008148 @default.
- W2251937247 hasConcept C41895202 @default.
- W2251937247 hasConcept C6557445 @default.
- W2251937247 hasConcept C80444323 @default.
- W2251937247 hasConcept C86803240 @default.
- W2251937247 hasConceptScore W2251937247C108010975 @default.
- W2251937247 hasConceptScore W2251937247C11413529 @default.
- W2251937247 hasConceptScore W2251937247C119857082 @default.
- W2251937247 hasConceptScore W2251937247C138885662 @default.
- W2251937247 hasConceptScore W2251937247C154945302 @default.
- W2251937247 hasConceptScore W2251937247C2776214188 @default.
- W2251937247 hasConceptScore W2251937247C2777472644 @default.
- W2251937247 hasConceptScore W2251937247C2779808786 @default.
- W2251937247 hasConceptScore W2251937247C41008148 @default.
- W2251937247 hasConceptScore W2251937247C41895202 @default.
- W2251937247 hasConceptScore W2251937247C6557445 @default.
- W2251937247 hasConceptScore W2251937247C80444323 @default.
- W2251937247 hasConceptScore W2251937247C86803240 @default.
- W2251937247 hasLocation W22519372471 @default.
- W2251937247 hasOpenAccess W2251937247 @default.
- W2251937247 hasPrimaryLocation W22519372471 @default.
- W2251937247 hasRelatedWork W2115836268 @default.
- W2251937247 hasRelatedWork W2129391075 @default.
- W2251937247 hasRelatedWork W2175676527 @default.
- W2251937247 hasRelatedWork W2250513825 @default.
- W2251937247 hasRelatedWork W2298902871 @default.
- W2251937247 hasRelatedWork W2473453452 @default.
- W2251937247 hasRelatedWork W2478464795 @default.
- W2251937247 hasRelatedWork W2513258002 @default.
- W2251937247 hasRelatedWork W2535143705 @default.
- W2251937247 hasRelatedWork W2619841328 @default.
- W2251937247 hasRelatedWork W2729183986 @default.
- W2251937247 hasRelatedWork W2884837949 @default.
- W2251937247 hasRelatedWork W2953898811 @default.
- W2251937247 hasRelatedWork W2955135267 @default.
- W2251937247 hasRelatedWork W2963090390 @default.
- W2251937247 hasRelatedWork W3088180619 @default.
- W2251937247 hasRelatedWork W3133661630 @default.
- W2251937247 hasRelatedWork W3185705705 @default.
- W2251937247 hasRelatedWork W783671439 @default.
- W2251937247 hasRelatedWork W974961824 @default.
- W2251937247 isParatext "false" @default.
- W2251937247 isRetracted "false" @default.
- W2251937247 magId "2251937247" @default.
- W2251937247 workType "article" @default.