Matches in SemOpenAlex for { <https://semopenalex.org/work/W2739639530> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2739639530 abstract "Existing sequence prediction methods are mostly concerned with time-independent sequences, in which the actual time span between events is irrelevant and the distance between events is simply the difference between their order positions in the sequence. While this time-independent view of sequences is applicable for data such as natural languages, e.g., dealing with words in a sentence, it is inappropriate and inefficient for many real world events that are observed and collected at unequally spaced points of time as they naturally arise, e.g., when a person goes to a grocery store or makes a phone call. The time span between events can carry important information about the sequence dependence of human behaviors. In this work, we propose a set of methods for using time in sequence prediction. Because neural sequence models such as RNN are more amenable for handling token-like input, we propose two methods for time-dependent event representation, based on the intuition on how time is tokenized in everyday life and previous work on embedding contextualization. We also introduce two methods for using next event duration as regularization for training a sequence prediction model. We discuss these methods based on recurrent neural nets. We evaluate these methods as well as baseline models on five datasets that resemble a variety of sequence prediction tasks. The experiments revealed that the proposed methods offer accuracy gain over baseline models in a range of settings." @default.
- W2739639530 created "2017-08-08" @default.
- W2739639530 creator A5017529415 @default.
- W2739639530 creator A5059941852 @default.
- W2739639530 creator A5064842058 @default.
- W2739639530 date "2017-07-31" @default.
- W2739639530 modified "2023-09-27" @default.
- W2739639530 title "Time-Dependent Representation for Neural Event Sequence Prediction" @default.
- W2739639530 hasPublicationYear "2017" @default.
- W2739639530 type Work @default.
- W2739639530 sameAs 2739639530 @default.
- W2739639530 citedByCount "0" @default.
- W2739639530 crossrefType "posted-content" @default.
- W2739639530 hasAuthorship W2739639530A5017529415 @default.
- W2739639530 hasAuthorship W2739639530A5059941852 @default.
- W2739639530 hasAuthorship W2739639530A5064842058 @default.
- W2739639530 hasConcept C107038049 @default.
- W2739639530 hasConcept C119857082 @default.
- W2739639530 hasConcept C121332964 @default.
- W2739639530 hasConcept C138885662 @default.
- W2739639530 hasConcept C147168706 @default.
- W2739639530 hasConcept C154945302 @default.
- W2739639530 hasConcept C2778112365 @default.
- W2739639530 hasConcept C2779466056 @default.
- W2739639530 hasConcept C2779662365 @default.
- W2739639530 hasConcept C38652104 @default.
- W2739639530 hasConcept C41008148 @default.
- W2739639530 hasConcept C48145219 @default.
- W2739639530 hasConcept C50644808 @default.
- W2739639530 hasConcept C54355233 @default.
- W2739639530 hasConcept C62520636 @default.
- W2739639530 hasConcept C86803240 @default.
- W2739639530 hasConceptScore W2739639530C107038049 @default.
- W2739639530 hasConceptScore W2739639530C119857082 @default.
- W2739639530 hasConceptScore W2739639530C121332964 @default.
- W2739639530 hasConceptScore W2739639530C138885662 @default.
- W2739639530 hasConceptScore W2739639530C147168706 @default.
- W2739639530 hasConceptScore W2739639530C154945302 @default.
- W2739639530 hasConceptScore W2739639530C2778112365 @default.
- W2739639530 hasConceptScore W2739639530C2779466056 @default.
- W2739639530 hasConceptScore W2739639530C2779662365 @default.
- W2739639530 hasConceptScore W2739639530C38652104 @default.
- W2739639530 hasConceptScore W2739639530C41008148 @default.
- W2739639530 hasConceptScore W2739639530C48145219 @default.
- W2739639530 hasConceptScore W2739639530C50644808 @default.
- W2739639530 hasConceptScore W2739639530C54355233 @default.
- W2739639530 hasConceptScore W2739639530C62520636 @default.
- W2739639530 hasConceptScore W2739639530C86803240 @default.
- W2739639530 hasLocation W27396395301 @default.
- W2739639530 hasOpenAccess W2739639530 @default.
- W2739639530 hasPrimaryLocation W27396395301 @default.
- W2739639530 hasRelatedWork W1758470730 @default.
- W2739639530 hasRelatedWork W2128358762 @default.
- W2739639530 hasRelatedWork W2313667075 @default.
- W2739639530 hasRelatedWork W2562877364 @default.
- W2739639530 hasRelatedWork W2741769313 @default.
- W2739639530 hasRelatedWork W2758362814 @default.
- W2739639530 hasRelatedWork W2886525390 @default.
- W2739639530 hasRelatedWork W2890549154 @default.
- W2739639530 hasRelatedWork W2950007497 @default.
- W2739639530 hasRelatedWork W2963469134 @default.
- W2739639530 hasRelatedWork W2970392559 @default.
- W2739639530 hasRelatedWork W2970733709 @default.
- W2739639530 hasRelatedWork W2973537767 @default.
- W2739639530 hasRelatedWork W3007997048 @default.
- W2739639530 hasRelatedWork W3014008432 @default.
- W2739639530 hasRelatedWork W3146217474 @default.
- W2739639530 hasRelatedWork W3160797086 @default.
- W2739639530 hasRelatedWork W3173899333 @default.
- W2739639530 hasRelatedWork W3198861570 @default.
- W2739639530 hasRelatedWork W65642710 @default.
- W2739639530 isParatext "false" @default.
- W2739639530 isRetracted "false" @default.
- W2739639530 magId "2739639530" @default.
- W2739639530 workType "article" @default.