Instance Weighting for Domain Adaptation in NLP

By Jing Jiang, Chengxiang Zhai. 2007

912 citations recorded by the source corpus.

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

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

In Representation & Self-Supervised Learning

Citations in the corpus

A theory of learning from different domains (2010, methodology): “This setting is motivated by several domain adaptation algorithms (Huang et al. 2007; Bickel et al. 2007; Jiang and Zhai 2007; Dai et al. 2007) that weigh the loss from training instances depending on how “far” they are from the target domain.”
A Theory of Multiple-Source Adaptation with Limited Target Labeled Data (2020, background): “…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 et al., 2007; Jiang and Zhai, 2007), speech processing (Gauvain and Lee, 1994; Jelinek, 1997), and computer vision (Leggetter and Woodland, 1995).”
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…”
Domain Adaptation: Learning Bounds and Algorithms (2009, background): “The problem of domain adaptation arises in a variety of applications in natural language processing (Dredze et al., 2007; Blitzer et al., 2007; Jiang & Zhai, 2007; Chelba & Acero, 2006; Daumé III & Marcu, 2006), speech processing (Legetter & Woodland, 1995; Gauvain & Chin-Hui, 1994; Pietra et al.,…”
Efficient Learning of Domain-invariant Image Representations (2013, neutral): “[16, 17, 18, 19] (see [20] for a comprehensive overview).”
How Transferable are Neural Networks in NLP Applications? (2016, methodology): “, 2010), instance weighting (Jiang and Zhai, 2007; Foster et al., 2010), and structural correspondence learning (Blitzer et al.”
An embarrassingly simple approach to zero-shot learning (2015, background): “The aim of domain adaptation is to learn a function from data in one domain, so that it can be successfully applied to data from a different domain [4, 8, 19].”
Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview (2019, background): “The community has long worked on the domain adaptation problem (Jiang and Zhai, 2007; Daume III, 2007): models fit on newswire data do not perform well on social media and other text types.”
A Comprehensive Survey on Transfer Learning (2019, background): “[34] J. Jiang and C. Zhai, “Instance weighting for domain adaptation in NLP,” in Proc.”
Learning to select data for transfer learning with Bayesian Optimization (2017, background): “Domain adaptation is a prominent approach to transfer learning that can help to bridge this gap; many approaches were suggested so far (Blitzer et al., 2007; Daumé III, 2007; Jiang and Zhai, 2007; Ma et al., 2014; Schnabel and Schütze, 2014).”
Deep CORAL: Correlation Alignment for Deep Domain Adaptation (2016, methodology): “Previous techniques for unsupervised adaptation consisted of re-weighting the training point losses to more closely reﬂect those in the test distribution [11,12] or ﬁnding a transformation in a lower-dimensional manifold that brings the source and target subspaces closer together.”
Multiple Source Adaptation and the Rényi Divergence (2009, background): “This problem arises in a variety of natu-ral language processing tasks such parsing, statistical language modeling, text classiﬁcation [15, 7, 16, 9, 10, 4, 6], or speech processing [11, 8, 14] and computer vision [13] tasks, as well as in many other applications.”
Return of Frustratingly Easy Domain Adaptation (2015, methodology): “Early techniques for unsupervised adaptation consisted of re-weighting the training point losses to more closely reflect those in the test distribution (Jiang and Zhai 2007; Huang et al. 2006).”
Supervised Representation Learning: Transfer Learning with Deep Autoencoders (2015, methodology): “…level, which aims to learn weights for the source domain labeled data, such that the reweighted source domain instances look similar to the target domain data instances [Dai et al., 2007b; Gao et al., 2008; Xing et al., 2007; Jiang and Zhai, 2007; Zhuang et al., 2010; Crammer et al., 2012].”
Domain Adaptation in Regression (2011, background): “But, a more challenging problem of domain adaptation arises in a variety of applications, including natural language processing, speech processing, or computer vision [7, 3, 9, 10, 17, 18, 12].”
Multi-domain learning by confidence-weighted parameter combination (2010, background): “…MD 21211, USA e-mail: mdredze@cs.jhu.edu A. Kulesza Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA 19104, USA e-mail: kulesza@cis.upenn.edu K. Crammer Department of Electrical Engineering, The Technion, Haifa 32000, Israel e-mail: koby@ee.technion.ac.il”
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation (2020, background): “…paradigms, moment matching and adversarial alignment, as aforementioned, there are several sample-based DA methods that estimate the importance weights of source samples (Jiang & Zhai, 2007; Huang et al., 2007) or sample-to-sample similarity via optimal transport (Bhushan Damodaran et al., 2018).”
Direct Density Ratio Estimation for Large-scale Covariate Shift Adaptation (2009, background): “bioinformatics [1, 5], spam filtering [4], natural language processing [14], brain-computer interfacing [28, 22], or econometrics [12], covariate shift is conceivable.”
Strong Baselines for Neural Semi-Supervised Learning under Domain Shift (2018, neutral): “, 2006, 2007) and instance weighting (Jiang and Zhai, 2007).”