Collaborative Multi-domain Sentiment Classification

57 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

An Overview of Multi-task Learning (2018, neutral): “…tagging, chunking, named entity recognition, semantic role labeling, language modeling and semantically related words) [116], multi-domain sentiment classification [117], multi-domain dialog state tracking [21], machine translation [118], syntactic parsing [118], and microblog analysis [119,120].”
A Survey on Multi-Task Learning (2017, methodology): “In [179], a multi-task model consisting of a general sparse learner for all the tasks and task-specific sparse learners which are regularized by pre-computed task similarities is proposed for multi-domain sentiment classification.”
Tackling Online Abuse: A Survey of Automated Abuse Detection Methods (2019, background): “Possible solutions for improving cross-domain abuse detection can be found in the literature of (adversarial) multi-task learning and domain adaptation (Daumé III, 2009; Ganin et al., 2016; Wu and Huang, 2015), and also in works such as that of Sharifirad et al.”
Multinomial Adversarial Networks for Multi-Domain Text Classification (2018, methodology): “We ﬁnd ﬁrst that MAN signiﬁcantly outperforms the state-of-the-art CMSC method (Wu and Huang, 2015) on the widely used multi-domain Amazon review dataset, and does so without relying on external resources such as sentiment lexica ( 4.1).”