brainsteam.co.uk/brainsteam/content/annotations/2022/11/21/1669061389.md

date	hypothesis-meta	in-reply-to	tags	type	url
2022-11-21T20:09:49	created document flagged group hidden id links permissions tags target text updated uri user user_info 2022-11-21T20:09:49.369906+00:00 title IEEEtran-7.pdf false __world__ false c71vQmnYEe2a7ffZp-667A html incontext json https://hypothes.is/a/c71vQmnYEe2a7ffZp-667A https://hyp.is/c71vQmnYEe2a7ffZp-667A/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/c71vQmnYEe2a7ffZp-667A admin delete read update acct:ravenscroftj@hypothes.is acct:ravenscroftj@hypothes.is group:__world__ acct:ravenscroftj@hypothes.is multi-task learning topic modelling NLProc selector source end start type 8039 7778 TextPositionSelector exact prefix suffix type e argue that mutual learningwould benefit sentiment classification since it enriches theinformation required for the training of the sentiment clas-sifier (e.g., when the word “incredible” is used to describe“acting” or “movie”, the polarity should be positive) thewords “acting” and “movie”. W . At thesame time, mutual learni 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 By training a topic model that has "similar" weights to the word vector model the sentiment task can also be improved (as per the example "incredible" should be positive when used to describe "acting" or "movie" in this context 2022-11-21T20:09:49.369906+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	multi-task learning topic modelling NLProc hypothesis	annotation	/annotation/2022/11/21/1669061389

e argue that mutual learningwould benefit sentiment classification since it enriches theinformation required for the training of the sentiment clas-sifier (e.g., when the word “incredible” is used to describe“acting” or “movie”, the polarity should be positive)

By training a topic model that has "similar" weights to the word vector model the sentiment task can also be improved (as per the example "incredible" should be positive when used to describe "acting" or "movie" in this context