brainsteam.co.uk/brainsteam/content/replies/2022/11/21/1669061242.md

date	hypothesis-meta	in-reply-to	tags	type	url
2022-11-21T20:07:22	created document flagged group hidden id links permissions tags target text updated uri user user_info 2022-11-21T20:07:22.691275+00:00 title IEEEtran-7.pdf false __world__ false HE4vnmnYEe2__KMWJ8Dgcg html incontext json https://hypothes.is/a/HE4vnmnYEe2__KMWJ8Dgcg 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 https://hypothes.is/api/annotations/HE4vnmnYEe2__KMWJ8Dgcg admin delete read update acct:ravenscroftj@hypothes.is acct:ravenscroftj@hypothes.is group:__world__ acct:ravenscroftj@hypothes.is NLProc multi-task learning topic modelling selector source end start type 5426 5187 TextPositionSelector exact prefix suffix type . 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 n task-relevant rep-resentations .We instead propose a new MTL fr TextQuoteSelector 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 Latent word vectors and topic models learn different and entirely unrelated representations 2022-11-21T20:07:22.691275+00:00 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 acct:ravenscroftj@hypothes.is display_name James Ravenscroft	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	NLProc multi-task learning topic modelling hypothesis	reply	/replies/2022/11/21/1669061242

. 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

Latent word vectors and topic models learn different and entirely unrelated representations