Matches in SemOpenAlex for { <https://semopenalex.org/work/W2977213636> ?p ?o ?g. }
- W2977213636 abstract "Topic models such as LDA, DocNADE, iDocNADEe have been popular in document analysis. However, the traditional topic models have several limitations including: (1) Bag-of-words (BoW) assumption, where they ignore word ordering, (2) Data sparsity, where the application of topic models is challenging due to limited word co-occurrences, leading to incoherent topics and (3) No Continuous Learning framework for topic learning in lifelong fashion, exploiting historical knowledge (or latent topics) and minimizing catastrophic forgetting. This thesis focuses on addressing the above challenges within neural topic modeling framework. We propose: (1) Contextualized topic model that combines a topic and a language model and introduces linguistic structures (such as word ordering, syntactic and semantic features, etc.) in topic modeling, (2) A novel lifelong learning mechanism into neural topic modeling framework to demonstrate continuous learning in sequential document collections and minimizing catastrophic forgetting. Additionally, we perform a selective data augmentation to alleviate the need for complete historical corpora during data hallucination or replay." @default.
- W2977213636 created "2019-10-03" @default.
- W2977213636 creator A5002518694 @default.
- W2977213636 creator A5020546938 @default.
- W2977213636 creator A5077629688 @default.
- W2977213636 date "2019-09-29" @default.
- W2977213636 modified "2023-09-27" @default.
- W2977213636 title "Lifelong Neural Topic Learning in Contextualized Autoregressive Topic Models of Language via Informative Transfers" @default.
- W2977213636 cites W1612003148 @default.
- W2977213636 cites W1614298861 @default.
- W2977213636 cites W1880262756 @default.
- W2977213636 cites W1950831375 @default.
- W2977213636 cites W2038043464 @default.
- W2977213636 cites W2064675550 @default.
- W2977213636 cites W2080021477 @default.
- W2977213636 cites W2097089247 @default.
- W2977213636 cites W2100002341 @default.
- W2977213636 cites W2116064496 @default.
- W2977213636 cites W2116825644 @default.
- W2977213636 cites W2131744502 @default.
- W2977213636 cites W2135181320 @default.
- W2977213636 cites W2145768976 @default.
- W2977213636 cites W2157006255 @default.
- W2977213636 cites W2161443453 @default.
- W2977213636 cites W2165279024 @default.
- W2977213636 cites W2178725228 @default.
- W2977213636 cites W2197590357 @default.
- W2977213636 cites W2250539671 @default.
- W2977213636 cites W2250753706 @default.
- W2977213636 cites W2397579082 @default.
- W2977213636 cites W2578454709 @default.
- W2977213636 cites W2617362271 @default.
- W2977213636 cites W2731782018 @default.
- W2977213636 cites W2798596203 @default.
- W2977213636 cites W2887906913 @default.
- W2977213636 cites W2891112648 @default.
- W2977213636 cites W2952723479 @default.
- W2977213636 cites W2962836999 @default.
- W2977213636 cites W2978365890 @default.
- W2977213636 cites W36903255 @default.
- W2977213636 cites W194249466 @default.
- W2977213636 hasPublicationYear "2019" @default.
- W2977213636 type Work @default.
- W2977213636 sameAs 2977213636 @default.
- W2977213636 citedByCount "0" @default.
- W2977213636 crossrefType "posted-content" @default.
- W2977213636 hasAuthorship W2977213636A5002518694 @default.
- W2977213636 hasAuthorship W2977213636A5020546938 @default.
- W2977213636 hasAuthorship W2977213636A5077629688 @default.
- W2977213636 hasConcept C108771440 @default.
- W2977213636 hasConcept C119857082 @default.
- W2977213636 hasConcept C137293760 @default.
- W2977213636 hasConcept C138885662 @default.
- W2977213636 hasConcept C154945302 @default.
- W2977213636 hasConcept C15744967 @default.
- W2977213636 hasConcept C171686336 @default.
- W2977213636 hasConcept C19417346 @default.
- W2977213636 hasConcept C204321447 @default.
- W2977213636 hasConcept C41008148 @default.
- W2977213636 hasConcept C41895202 @default.
- W2977213636 hasConcept C7149132 @default.
- W2977213636 hasConcept C90805587 @default.
- W2977213636 hasConceptScore W2977213636C108771440 @default.
- W2977213636 hasConceptScore W2977213636C119857082 @default.
- W2977213636 hasConceptScore W2977213636C137293760 @default.
- W2977213636 hasConceptScore W2977213636C138885662 @default.
- W2977213636 hasConceptScore W2977213636C154945302 @default.
- W2977213636 hasConceptScore W2977213636C15744967 @default.
- W2977213636 hasConceptScore W2977213636C171686336 @default.
- W2977213636 hasConceptScore W2977213636C19417346 @default.
- W2977213636 hasConceptScore W2977213636C204321447 @default.
- W2977213636 hasConceptScore W2977213636C41008148 @default.
- W2977213636 hasConceptScore W2977213636C41895202 @default.
- W2977213636 hasConceptScore W2977213636C7149132 @default.
- W2977213636 hasConceptScore W2977213636C90805587 @default.
- W2977213636 hasLocation W29772136361 @default.
- W2977213636 hasOpenAccess W2977213636 @default.
- W2977213636 hasPrimaryLocation W29772136361 @default.
- W2977213636 hasRelatedWork W1257686400 @default.
- W2977213636 hasRelatedWork W1758764730 @default.
- W2977213636 hasRelatedWork W2807739445 @default.
- W2977213636 hasRelatedWork W2891112648 @default.
- W2977213636 hasRelatedWork W2972327144 @default.
- W2977213636 hasRelatedWork W2974495808 @default.
- W2977213636 hasRelatedWork W2981916418 @default.
- W2977213636 hasRelatedWork W2994978584 @default.
- W2977213636 hasRelatedWork W2996260170 @default.
- W2977213636 hasRelatedWork W3028100809 @default.
- W2977213636 hasRelatedWork W3032414079 @default.
- W2977213636 hasRelatedWork W3047601251 @default.
- W2977213636 hasRelatedWork W3089984973 @default.
- W2977213636 hasRelatedWork W3092169936 @default.
- W2977213636 hasRelatedWork W3106926072 @default.
- W2977213636 hasRelatedWork W3123259583 @default.
- W2977213636 hasRelatedWork W3155004718 @default.
- W2977213636 hasRelatedWork W3163510162 @default.
- W2977213636 hasRelatedWork W3173847981 @default.
- W2977213636 hasRelatedWork W3209739561 @default.
- W2977213636 isParatext "false" @default.
- W2977213636 isRetracted "false" @default.