Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification

By John Blitzer, Mark Dredze, Fernando C Pereira. 2007

2,427 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

Universal Language Model Fine-tuning for Text Classification (2018, background): “Research in NLP focused mostly on transductive transfer (Blitzer et al., 2007).”
Pretrained Transformers Improve Out-of-Distribution Robustness (2020, background): “Other research on robustness considers the separate problem of domain adaptation (Blitzer et al., 2007; Daumé III, 2007), where models must learn representations of a source and target distribution.”
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].”
Multiple-Source Adaptation with Domain Classifiers (2020, methodology): “…are available for some source domains such as TVs, laptops and CD players, each previously trained on labeled data, but no labeled data or predictor is at hand for the broader category of electronics, which can be viewed as a mixture of the sub-domains [Blitzer et al., 2007, Dredze et al., 2008].”
A Theory of Multiple-Source Adaptation with Limited Target Labeled Data (2020, background): “How can we leverage the labeled data from these source domains to come up with an accurate predictor for the target domain? This is the challenge of the domain adaptation problem that arises in a variety of di↵erent applications, such as in natural language processing (Blitzer et al., 2007; Dredze e”
Agnostic Federated Learning (2019, methodology): “This also includes previous applications in natural language processing (Dredze et al., 2007; Blitzer et al., 2007; Jiang and Zhai, 2007; Raju et al., 2018), speech recognition (Legetter and Woodland, 1995; Gauvain and Chin-Hui, 1994; Pietra et al., 1992; Rosenfeld, 1996; Jelinek, 1998; Roark and…”
Algorithms and Theory for Multiple-Source Adaptation (2018, methodology): “Next, we evaluate our DC-programming solution applied to real-world datasets: a sentiment analysis dataset [Blitzer et al., 2007] for squared loss, a visual domain adaptation benchmark dataset Ofﬁce [Saenko et al., 2010], as well as a generalization of digit recognition task, for cross-entropy loss.”
An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks (2013, methodology): “To test this case, we used sentiment analysis of two product categories of Amazon reviews (Blitzer et al., 2007) as the two tasks.”
Multi-Source Domain Adaptation: A Causal View (2015, methodology): “The sentiment data (Blitzer, Dredze, and Pereira 2007) consist of review text and labels for four categories of goods (domains): book, dvd, electronics, and kitchen; each domain contains 2000 data points (or reviews) with four labels (or classes).”
Regularizing Text Categorization with Clusters of Words (2016, methodology): “The sentiment analysis datasets we examined include movie reviews 2http://qwone.com/~jason/20Newsgroups/ (Pang and Lee, 2004; Zaidan and Eisner, 2008)3, floor speeches by U.S. Congressmen deciding “yea"/“nay" votes on the bill under discussion (Thomas et al., 2006)3 and product reviews from Amazon (”
Text Categorization as a Graph Classification Problem (2015, background): “• Amazon: 8,000 product reviews over four different sub-collections (books, DVDs, electronics and kitchen appliances) classified as positive or negative – split into 1,600 for training and 400 for test each (Blitzer et al., 2007).”