Aspect-augmented Adversarial Networks for Domain Adaptation
Citations
645 citations
644 citations
Cites methods from "Aspect-augmented Adversarial Networ..."
...Outside of sequence generation, Chen et al. (2016b) apply the idea of adversarial training to sentiment analysis and Zhang et al. (2017) apply the idea to domain adaptation tasks....
[...]
641 citations
Cites methods from "Aspect-augmented Adversarial Networ..."
...Furthermore, our approach was inspired by the effectiveness of adversarial learning for various applications, like learning discriminative image features [17], or (un)supervised domain adaptation to enforce domain-invariant features [2, 6, 41], and regularizing correlation loss between cross-modal items [10]....
[...]
496 citations
Cites background or methods from "Aspect-augmented Adversarial Networ..."
...[275] found a CNN to work just as well as RNNs or bi-LSTMs in their experiments....
[...]
...[275] weight examples by their relevance to their target aspect based on a small set of positive and negative keywords (a form of weak supervision)....
[...]
...Domain adaptation has been used in natural language processing such as for sentiment analysis (Table 4, [275, 282]), other text classification [144, 275] including weakly-supervised aspect-transfer from one aspect of a dataset to another [275], relation extraction [70], semi-supervised sequence labeling [54], semi-supervised question answering [262], sentence specificity [119], and neural machine translation [23, 31, 42]....
[...]
296 citations
Cites background from "Aspect-augmented Adversarial Networ..."
...…with adversarial learning, e.g., video analysis (Hoffman et al., 2016; Shrivastava et al., 2016; Hoffman et al., 2017; Tzeng et al., 2017), natural language understanding (Zhang et al., 2017; Fu et al., 2017), speech recognition (Zhao et al., 2019; Hosseini-Asl et al., 2018), to name a few....
[...]
...In fact, despite being successfully applied in various applications (Zhang et al., 2017; Hoffman et al., 2017), it has also been reported that such methods fail to generalize in certain closely related source/target pairs, e.g., digit classification from MNIST to SVHN (Ganin et al., 2016)....
[...]
...In fact, despite being successfully applied in various applications (Zhang et al., 2017; Hoffman et al., 2017), it has also been reported that such methods fail to generalize in certain closely related source/target pairs, e....
[...]
..., 2017), natural language understanding (Zhang et al., 2017; Fu et al., 2017), speech recognition (Zhao et al....
[...]
References
38,211 citations
"Aspect-augmented Adversarial Networ..." refers methods in this paper
...Adversarial networks have originally been developed for image generation (Goodfellow et al., 2014; Makhzani et al., 2015; Springenberg, 2015; Radford et al., 2015; Taigman et al., 2016), and later applied to domain adaption in computer vision (Ganin and Lempitsky, 2014; Ganin et al....
[...]
...Adversarial networks were originally developed for image generation (Goodfellow et al., 2014; Makhzani et al., 2015; Springenberg, 2015; Radford et al., 2015; Taigman et al., 2016), and were later applied to domain adaptation in computer vision (Ganin and Lempitsky, 2014; Ganin et al., 2015;…...
[...]
30,843 citations
"Aspect-augmented Adversarial Networ..." refers methods in this paper
...We also apply batch normalization (Ioffe and Szegedy, 2015) on the sentence encoder and apply dropout with ratio 0....
[...]
20,027 citations
"Aspect-augmented Adversarial Networ..." refers background or methods in this paper
...…models typically induce attention in an unsupervised manner, they have to rely on a large amount of labeled data for the target task (Bahdanau et al., 2014; Rush et al., 2015; Chen et al., 2015; Cheng et al., 2016; Xu et al., 2015; Xu and Saenko, 2015; Yang et al., 2015; Martins and…...
[...]
...While traditional attention-based models typically induce attention in an unsupervised manner, they have to rely on a large amount of labeled data for the target task (Bahdanau et al., 2014; Rush et al., 2015; Chen et al., 2015; Cheng et al., 2016; Xu et al., 2015; Xu and Saenko, 2015; Yang et al., 2015; Martins and Astudillo, 2016; Lei et al., 2016)....
[...]
18,616 citations
"Aspect-augmented Adversarial Networ..." refers background in this paper
...(Caruana, 1998; Pan and Yang, 2010; Collobert and Weston, 2008; Liu et al., 2015; Bordes et al., 2012)....
[...]
17,184 citations