From 618aa0590540d9b5c03a124b1337baf2fc5376dd Mon Sep 17 00:00:00 2001 From: ravenscroftj Date: Mon, 21 Nov 2022 20:15:04 +0000 Subject: [PATCH] Add 'brainsteam/content/replies/2022/11/21/1669061585.md' --- .../content/replies/2022/11/21/1669061585.md | 73 +++++++++++++++++++ 1 file changed, 73 insertions(+) create mode 100644 brainsteam/content/replies/2022/11/21/1669061585.md diff --git a/brainsteam/content/replies/2022/11/21/1669061585.md b/brainsteam/content/replies/2022/11/21/1669061585.md new file mode 100644 index 0000000..b748441 --- /dev/null +++ b/brainsteam/content/replies/2022/11/21/1669061585.md @@ -0,0 +1,73 @@ +--- +date: '2022-11-21T20:13:05' +hypothesis-meta: + created: '2022-11-21T20:13:05.556810+00:00' + document: + title: + - IEEEtran-7.pdf + flagged: false + group: __world__ + hidden: false + id: 6KsbkmnYEe2Y3g9fobLUFA + links: + html: https://hypothes.is/a/6KsbkmnYEe2Y3g9fobLUFA + incontext: https://hyp.is/6KsbkmnYEe2Y3g9fobLUFA/www.researchgate.net/profile/Lin-Gui-5/publication/342058196_Multi-Task_Learning_with_Mutual_Learning_for_Joint_Sentiment_Classification_and_Topic_Detection/links/5f96fd48458515b7cf9f3abd/Multi-Task-Learning-with-Mutual-Learning-for-Joint-Sentiment-Classification-and-Topic-Detection.pdf + json: https://hypothes.is/api/annotations/6KsbkmnYEe2Y3g9fobLUFA + permissions: + admin: + - acct:ravenscroftj@hypothes.is + delete: + - acct:ravenscroftj@hypothes.is + read: + - group:__world__ + update: + - acct:ravenscroftj@hypothes.is + tags: + - NLProc + - topic modelling + - neural networks + target: + - selector: + - end: 11125 + start: 10591 + type: TextPositionSelector + - exact: n recent years, the neural network based topic modelshave been proposed + for many NLP tasks, such as infor-mation retrieval [11], aspect extraction + [12] and sentimentclassification [13]. The basic idea is to construct a neuralnetwork + which aims to approximate the topic-word distri-bution in probabilistic topic + models. Additional constraints,such as incorporating prior distribution [14], + enforcing di-versity among topics [15] or encouraging topic sparsity [16],have + been explored for neural topic model learning andproved effective. + prefix: ' word embeddings[8], [9], [10].I' + suffix: ' However, most of these algorith' + type: TextQuoteSelector + source: https://www.researchgate.net/profile/Lin-Gui-5/publication/342058196_Multi-Task_Learning_with_Mutual_Learning_for_Joint_Sentiment_Classification_and_Topic_Detection/links/5f96fd48458515b7cf9f3abd/Multi-Task-Learning-with-Mutual-Learning-for-Joint-Sentiment-Classification-and-Topic-Detection.pdf + text: "Neural topic models are often trained to mimic the behaviours of probabilistic\ + \ topic models - I should come back and look at some of the works:\n\n* R. Das,\ + \ M. Zaheer, and C. Dyer, \u201CGaussian LDA for topic models with word embeddings,\u201D\ + \ \n* P. Xie, J. Zhu, and E. P. Xing, \u201CDiversity-promoting bayesian learning\ + \ of latent variable models,\u201D\n * M. Peng, Q. Xie, H. Wang, Y. Zhang, X.\ + \ Zhang, J. Huang, and G. Tian, \u201CNeural sparse topical coding,\u201D" + updated: '2022-11-21T20:13:05.556810+00:00' + uri: https://www.researchgate.net/profile/Lin-Gui-5/publication/342058196_Multi-Task_Learning_with_Mutual_Learning_for_Joint_Sentiment_Classification_and_Topic_Detection/links/5f96fd48458515b7cf9f3abd/Multi-Task-Learning-with-Mutual-Learning-for-Joint-Sentiment-Classification-and-Topic-Detection.pdf + user: acct:ravenscroftj@hypothes.is + user_info: + display_name: James Ravenscroft +in-reply-to: https://www.researchgate.net/profile/Lin-Gui-5/publication/342058196_Multi-Task_Learning_with_Mutual_Learning_for_Joint_Sentiment_Classification_and_Topic_Detection/links/5f96fd48458515b7cf9f3abd/Multi-Task-Learning-with-Mutual-Learning-for-Joint-Sentiment-Classification-and-Topic-Detection.pdf +tags: +- NLProc +- topic modelling +- neural networks +- hypothesis +type: reply +url: /replies/2022/11/21/1669061585 + +--- + + + +
n recent years, the neural network based topic modelshave been proposed for many NLP tasks, such as infor-mation retrieval [11], aspect extraction [12] and sentimentclassification [13]. The basic idea is to construct a neuralnetwork which aims to approximate the topic-word distri-bution in probabilistic topic models. Additional constraints,such as incorporating prior distribution [14], enforcing di-versity among topics [15] or encouraging topic sparsity [16],have been explored for neural topic model learning andproved effective.
Neural topic models are often trained to mimic the behaviours of probabilistic topic models - I should come back and look at some of the works: + +* R. Das, M. Zaheer, and C. Dyer, “Gaussian LDA for topic models with word embeddings,” +* P. Xie, J. Zhu, and E. P. Xing, “Diversity-promoting bayesian learning of latent variable models,” + * M. Peng, Q. Xie, H. Wang, Y. Zhang, X. Zhang, J. Huang, and G. Tian, “Neural sparse topical coding,” \ No newline at end of file