Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
A theory of learning from different domains
20092.0k citationsJohn Blitzer, Koby Crammer et al.profile →
This map shows the geographic impact of John Blitzer's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by John Blitzer with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites John Blitzer more than expected).
This network shows the impact of papers produced by John Blitzer. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by John Blitzer. The network helps show where John Blitzer may publish in the future.
Co-authorship network of co-authors of John Blitzer
This figure shows the co-authorship network connecting the top 25 collaborators of John Blitzer.
A scholar is included among the top collaborators of John Blitzer based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with John Blitzer. John Blitzer is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
Weston, Jason & John Blitzer. (2012). Latent structured ranking. Uncertainty in Artificial Intelligence. 903–913.6 indexed citations
2.
Chen, Minmin, Kilian Q. Weinberger, & John Blitzer. (2011). Co-Training for Domain Adaptation. Neural Information Processing Systems. 24. 2456–2464.256 indexed citations
3.
Blitzer, John, Sham M. Kakade, & Dean P. Foster. (2011). Domain Adaptation with Coupled Subspaces. ScholarlyCommons (University of Pennsylvania). 15. 173–181.62 indexed citations
Dredze, Mark, et al.. (2008). Intelligent email: aiding users with AI. ScholarWorks@UMassAmherst (University of Massachusetts Amherst). 1524–1527.15 indexed citations
8.
Blitzer, John, et al.. (2008). Regularized Learning with Networks of Features. Neural Information Processing Systems. 21. 1401–1408.30 indexed citations
9.
Dredze, Mark, et al.. (2008). Intelligent email. 321–324.21 indexed citations
Blitzer, John, Koby Crammer, Alex Kulesza, Fernando Pereira, & Jennifer R. Wortman. (2007). Learning Bounds for Domain Adaptation. Neural Information Processing Systems. 20. 129–136.215 indexed citations
Dredze, Mark, et al.. (2007). Frustratingly Hard Domain Adaptation for Dependency Parsing. Empirical Methods in Natural Language Processing. 1051–1055.57 indexed citations
14.
Dredze, Mark, John Blitzer, & Fernando Pereira. (2006). "Sorry, I Forgot the Attachment:" Email Attachment Prediction.2 indexed citations
15.
Blitzer, John, Ryan McDonald, & Fernando Pereira. (2006). Domain adaptation with structural correspondence learning. 120–120.985 indexed citations breakdown →
16.
Blitzer, John, Amir Globerson, & Fernando Pereira. (2005). Distributed Latent Variable Models of Lexical Co-occurrences.. International Conference on Artificial Intelligence and Statistics. 48(2). 113–28.13 indexed citations
Dredze, Mark, John Blitzer, & Fernando Pereira. (2005). Reply Expectation Prediction for Email Management..13 indexed citations
19.
Blitzer, John, Fernando Pereira, Kilian Q. Weinberger, & Lawrence K. Saul. (2004). Hierarchical Distributed Representations for Statistical Language Modeling. ScholarlyCommons (University of Pennsylvania). 17. 185–192.18 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.