Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach

By Xavier Glorot, Antoine Bordes, Yoshua Bengio. 2011

1,861 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.

In Natural Language Processing

Citations in the corpus

Distributed Representations of Words and Phrases and their Compositionality (2013, background): “The follow up work includes applications to automatic speech recognition and machine translation [14, 7], and a wide range of NLP tasks [2, 20, 15, 3, 18, 19, 9].”
Better Mixing via Deep Representations (2012, background): “Several observations suggest that some deep learning algorithms indeed help to disentangle the underlying factors of variation (Goodfellow et al., 2009; Glorot et al., 2011).”
Zero-Shot Learning Through Cross-Modal Transfer (2013, background): “For instance, in sentiment analysis one could train a classiﬁer for movie reviews and then adapt from that domain to book reviews [4, 13].”
Refining Language Models with Compositional Explanations (2021, background): “In another relevant thread, unsupervised domain adaptation (UDA) looks to adapt a trained model to a new domain using unlabeled data from the target domain, by updating feature representation to minimize the distribution divergence between domains [12, 11], or updating models to match the distributi”
Semi-Supervised QA with Generative Domain-Adaptive Nets (2017, background): “Several techniques on domain adaptation (Glorot et al., 2011) focus on learning distribution invariant features by sharing the intermediate representations for downstream tasks.”
Domain-Adversarial Training of Neural Networks (2015, methodology): “This improves over a similar approach of Glorot et al. (2011) that simply trains a single deep autoencoder for both domains.”
How to Construct Deep Recurrent Neural Networks (2013, methodology): “Previous work has shown that higher-level representations of deep networks tend to better disentangle the underlying factors of variation than the original input (Goodfellow et al. , 2009; Glorot et al. , 2011b) and ﬂatten the manifolds near which the data concentrate (Bengio et al. , 2013).”
Learning Transferable Features with Deep Adaptation Networks (2015, background): “It reveals a surprising observation that ˆ d A on CNN features is larger than ˆ d A on raw features, which implies worse generalization bound (Glorot et al., 2011).”
Compressing Neural Networks with the Hashing Trick (2015, methodology): “The “inﬂation” of neural networks with HashedNets imposes no restrictions on other network architecture design choices, such as dropout regularization (Srivastava et al., 2014), activation functions (Glorot et al., 2011a; LeCun et al., 2012), or weight sparsity (Coates et al., 2011).”
Marginalized Denoising Autoencoders for Domain Adaptation (2012, methodology): “Following Glorot et al. (2011), we evaluate our results with the transfer error e ( S, T ) and the in-domain error e ( T, T ) .”
An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks (2013, methodology): “Rectiﬁed linear (Jarrett et al., 2009; Glorot et al., 2011a): et al., 2013): Here g is a gating function. z is divided into disjoint blocks of size k , and g ( i, z ) is 1 if z i is the maximal element of its group.”
A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines (2018, neutral): “Although they have been successfully used in [47,48], the authors had to resort to a few detours.”
Isolating Sources of Disentanglement in VAEs (2018, background): “Prior to β -VAE [7], some have shown successful disentanglement in limited settings with few factors of variation [1, 14, 30, 31].”