--- date: '2022-11-21T20:07:22' hypothesis-meta: created: '2022-11-21T20:07:22.691275+00:00' document: title: - IEEEtran-7.pdf flagged: false group: __world__ hidden: false id: HE4vnmnYEe2__KMWJ8Dgcg links: html: https://hypothes.is/a/HE4vnmnYEe2__KMWJ8Dgcg incontext: https://hyp.is/HE4vnmnYEe2__KMWJ8Dgcg/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/HE4vnmnYEe2__KMWJ8Dgcg permissions: admin: - acct:ravenscroftj@hypothes.is delete: - acct:ravenscroftj@hypothes.is read: - group:__world__ update: - acct:ravenscroftj@hypothes.is tags: - NLProc - multi-task learning - topic modelling target: - selector: - end: 5426 start: 5187 type: TextPositionSelector - exact: . However, such a framework is not applicablehere since the learned latent topic representations in topicmodels can not be shared directly with word or sentencerepresentations learned in classifiers, due to their differentinherent meanings prefix: n task-relevant rep-resentations suffix: .We instead propose a new MTL fr 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: Latent word vectors and topic models learn different and entirely unrelated representations updated: '2022-11-21T20:07:22.691275+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 - multi-task learning - topic modelling - hypothesis type: annotation url: /annotation/2022/11/21/1669061242 --- <blockquote>. However, such a framework is not applicablehere since the learned latent topic representations in topicmodels can not be shared directly with word or sentencerepresentations learned in classifiers, due to their differentinherent meanings</blockquote>Latent word vectors and topic models learn different and entirely unrelated representations