Hal Daumé

17.3k citations
183 papers · 10.0k · 7 hit papers · h-index 47

Impact in

    • Topic Modeling
    • Natural Language Processing Techniques
    • Domain Adaptation and Few-Shot Learning
    • Advanced Text Analysis Techniques
    • Text and Document Classification Technologies
    • Multimodal Machine Learning Applications
    • Advanced Image and Video Retrieval Techniques
    • Face and Expression Recognition

Papers in

    • Topic Modeling 84
    • Natural Language Processing Techniques 63
    • Machine Learning and Algorithms 17
    • Advanced Text Analysis Techniques 13
    • Machine Learning and Data Classification 12
    • Domain Adaptation and Few-Shot Learning 11
    • Multimodal Machine Learning Applications 20
    • Advanced Image and Video Retrieval Techniques 12

Hal Daumé

173 papers receiving 9.5k citations

Hal Daumé's Hit Papers

Improving Fairness in Machine Learning Systems 2019 · 556 citations
5560+6+13Years since publication250500750

Peers

Hal Daumé
Comparison fields: 5 of 167
  • Artificial Intelligence 6.8k
  • Computer Vision and Pattern Recognition 3.6k
  • Health Informatics 147
  • Computational Mathematics 47
  • Computer Science Applications 392
Replace Vicente Ordóñez with:
Vicente Ordóñez United States
Hanna Wallach United States
Alexander M. Rush United States
Mor Naaman United States
Percy Liang United States
Noah A. Smith United States
Haoran Xie Hong Kong
Yoav Goldberg Israel
Yangqiu Song Hong Kong
Hanghang Tong United States
Hal Daumé relative to Vicente Ordóñez United States Vicente Ordóñez's profile →
Citations per field
00.5×2×3×4.1×
Vicente Ordóñez · 1×
Citations per year

Countries citing papers authored by Hal Daumé

Since Specialization
Citations

This map shows the geographic impact of Hal Daumé'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 Hal Daumé with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Hal Daumé more than expected).

Fields of papers citing papers by Hal Daumé

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Hal Daumé. 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 Hal Daumé. The network helps show where Hal Daumé may publish in the future.

Co-authors

The 25 scholars most cited alongside Hal Daumé, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Hal Daumé Line = papers co-authored together Hal Daumé links everyone, so they are left out of the graph.

All Works

20 of 20 papers shown

Showing the 20 most-cited of 183 papers — load more, or switch the sort, to bring in the rest.

#Work
1
Co-regularized Multi-view Spectral Clustering
Hit paper breakdown →
2011761
2
Generalized Multiview Analysis: A discriminative latent space
Hit paper breakdown →
2012601
3
Domain Adaptation for Statistical Classifiers
Hit paper breakdown →
2006593
4
Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Hit paper breakdown →
2013578
5
Improving Fairness in Machine Learning Systems
Hit paper breakdown →
2019556
6
A Co-training Approach for Multi-view Spectral Clustering
Hit paper breakdown →
2011546
7
Deep Unordered Composition Rivals Syntactic Methods for Text Classification
Hit paper breakdown →
2015530
8
Midge: Generating Image Descriptions From Computer Vision Detections
2012289
9 2009266
10
Corpus-Guided Sentence Generation of Natural Images
2011254
11 2014223
12 2006185
13
Incorporating Lexical Priors into Topic Models
2010174
14 2018163
15
Frustratingly Easy Semi-Supervised Domain Adaptation
2010125
16 2012119
17
Co-regularization Based Semi-supervised Domain Adaptation
2010110
18 2005107
19 2018107
20 201697

About Hal Daumé

Hal Daumé is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition, Computer Science Applications, Safety Research and Information Systems, having authored 183 papers that have together received 10.0k indexed citations. Recurring topics across this work include Topic Modeling (84 papers), Natural Language Processing Techniques (63 papers), Multimodal Machine Learning Applications (20 papers), Machine Learning and Algorithms (17 papers), Advanced Text Analysis Techniques (13 papers), Advanced Image and Video Retrieval Techniques (12 papers), Machine Learning and Data Classification (12 papers) and Domain Adaptation and Few-Shot Learning (11 papers). The work is most often cited by research in Artificial Intelligence (6.8k citations), Computer Vision and Pattern Recognition (3.6k citations), Health Informatics (147 citations), Computational Mathematics (47 citations) and Computer Science Applications (392 citations). Hal Daumé has collaborated with scholars based in United States, United Kingdom and Canada. Frequent co-authors include Daniel Marcu, Abhishek Kumar, Piyush Rai, Jordan Lee Boyd-Graber, Mohit Iyyer, Lucy Vanderwende, Katrin Kirchhoff, Abhishek Sharma, Anurag Kumar and Jagadeesh Jagarlamudi. Their work appears in journals such as PLoS ONE, Transactions of the Association for Computational Linguistics, Proceedings of the ACM on Human-Computer Interaction, Machine Learning and Computational Linguistics.

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.

Explore authors with similar magnitude of impact