Dekai Wu

4.2k total citations · 1 hit paper
123 papers, 2.4k citations indexed

About

Dekai Wu is a scholar working on Artificial Intelligence, Computational Theory and Mathematics and Signal Processing. According to data from OpenAlex, Dekai Wu has authored 123 papers receiving a total of 2.4k indexed citations (citations by other indexed papers that have themselves been cited), including 115 papers in Artificial Intelligence, 7 papers in Computational Theory and Mathematics and 6 papers in Signal Processing. Recurrent topics in Dekai Wu's work include Natural Language Processing Techniques (104 papers), Topic Modeling (92 papers) and Speech and dialogue systems (27 papers). Dekai Wu is often cited by papers focused on Natural Language Processing Techniques (104 papers), Topic Modeling (92 papers) and Speech and dialogue systems (27 papers). Dekai Wu collaborates with scholars based in Hong Kong, United States and Sweden. Dekai Wu's co-authors include Marine Carpuat, Chi-kiu Lo, Pascale Fung, Grace Ngai, Joakim Nivre, Weifeng Su, Yongsheng Yang, Andreas Stolcke, Anders Søgaard and Robert Wilensky and has published in prestigious journals such as IEEE Transactions on Medical Imaging, Behavioral and Brain Sciences and Artificial Intelligence Review.

In The Last Decade

Dekai Wu

115 papers receiving 2.0k citations

Hit Papers

Stochastic inversion transduction grammars and bilingual ... 1997 2026 2006 2016 1997 200 400 600

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Dekai Wu Hong Kong 23 2.4k 157 120 110 95 123 2.4k
Jens Nilsson Sweden 16 2.0k 0.9× 181 1.2× 130 1.1× 176 1.6× 67 0.7× 30 2.2k
Johan Hall Sweden 15 1.8k 0.8× 139 0.9× 169 1.4× 161 1.5× 44 0.5× 31 2.0k
Giorgio Satta Italy 19 1.3k 0.6× 146 0.9× 79 0.7× 81 0.7× 340 3.6× 102 1.4k
Ann Bies United States 14 1.3k 0.5× 176 1.1× 84 0.7× 107 1.0× 25 0.3× 44 1.4k
Sandra Kübler United States 17 2.1k 0.9× 120 0.8× 119 1.0× 217 2.0× 30 0.3× 97 2.2k
Carlos Gómez‐Rodríguez Spain 19 991 0.4× 84 0.5× 50 0.4× 198 1.8× 70 0.7× 91 1.1k
Adam Lopez United Kingdom 21 1.3k 0.5× 126 0.8× 165 1.4× 105 1.0× 33 0.3× 64 1.4k
Philipp Koehn United Kingdom 4 2.1k 0.9× 114 0.7× 256 2.1× 136 1.2× 28 0.3× 7 2.2k
Daisuke Kawahara Japan 19 1.3k 0.6× 78 0.5× 127 1.1× 193 1.8× 30 0.3× 139 1.5k
Deniz Yüret Türkiye 17 1.2k 0.5× 153 1.0× 136 1.1× 91 0.8× 35 0.4× 61 1.4k

Countries citing papers authored by Dekai Wu

Since Specialization
Citations

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

Fields of papers citing papers by Dekai Wu

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Dekai Wu

This figure shows the co-authorship network connecting the top 25 collaborators of Dekai Wu. A scholar is included among the top collaborators of Dekai Wu 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 Dekai Wu. Dekai Wu 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.
Wu, Dekai, et al.. (2015). Learning to rap battle with bilingual recursive neural networks. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 2524–2530. 2 indexed citations
2.
Lo, Chi-kiu, et al.. (2013). Improving machine translation by training against an automatic semantic frame based evaluation metric. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 375–381. 14 indexed citations
3.
Wu, Dekai, et al.. (2013). Bayesian Induction of Bracketing Inversion Transduction Grammars. International Joint Conference on Natural Language Processing. 1158–1166. 1 indexed citations
4.
Lo, Chi-kiu, et al.. (2012). Accuracy and robustness in measuring the lexical similarity of semantic role fillers for automatic semantic MT evaluation. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 574–581. 7 indexed citations
5.
Lo, Chi-kiu & Dekai Wu. (2011). MEANT: An inexpensive, high-accuracy, semi-automatic metric for evaluating translation utility based on semantic roles. Meeting of the Association for Computational Linguistics. 1. 220–229. 55 indexed citations
6.
Lo, Chi-kiu & Dekai Wu. (2011). Structured vs. Flat Semantic Role Representations for Machine Translation Evaluation. Meeting of the Association for Computational Linguistics. 10–20. 11 indexed citations
7.
Lo, Chi-kiu & Dekai Wu. (2011). SMT versus AI redux: how semantic fames evaluate MT more accurately. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 1838–1845. 6 indexed citations
8.
Nivre, Joakim, et al.. (2010). Linear Inversion Transduction Grammar Alignments as a Second Translation Path. Workshop on Statistical Machine Translation. 167–171. 1 indexed citations
9.
Lo, Chi-kiu & Dekai Wu. (2010). Evaluating Machine Translation Utility via Semantic Role Labels. Language Resources and Evaluation. 8 indexed citations
10.
Wu, Dekai & David Chiang. (2009). Proceedings of the Third Workshop on Syntax and Structure in Statistical Translation (SSST-3) at NAACL HLT 2009. North American Chapter of the Association for Computational Linguistics. 2 indexed citations
11.
Wu, Dekai & David Chiang. (2008). Proceedings of SSST-2, Second Workshop on Syntax and Structure in Statistical Translation. Meeting of the Association for Computational Linguistics. 1 indexed citations
12.
Carpuat, Marine & Dekai Wu. (2007). Improving Statistical Machine Translation Using Word Sense Disambiguation. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 61–72. 230 indexed citations
13.
Carpuat, Marine & Dekai Wu. (2005). Evaluating the Word Sense Disambiguation Performance of Statistical Machine Translation. International Joint Conference on Natural Language Processing. 18 indexed citations
14.
Carpuat, Marine, Weifeng Su, & Dekai Wu. (2004). Augmenting Ensemble Classification for Word Sense Disambiguation with a Kernel PCA Model. Meeting of the Association for Computational Linguistics. 88–92. 13 indexed citations
15.
Wu, Dekai, et al.. (1999). Automatically Merging Lexicons that have Incompatible Part-of-Speech Categories. Empirical Methods in Natural Language Processing. 3 indexed citations
16.
Wu, Dekai, et al.. (1995). Using Brackets to Improve Search for Statistical Machine Translation. Pacific Asia Conference on Language, Information, and Computation. 195–204. 2 indexed citations
17.
Wu, Dekai. (1995). Stochastic inversion transduction grammars with application to segmentation, bracketing, and alignment of parallel corpora. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 1328–1335. 49 indexed citations
18.
Wu, Dekai. (1994). Review of Statistically-driven computer grammars of English: the IBM/lancaster approach by Ezra Black, Roger Garside, and Geoffrey Leech. Editions Rodopi 1993.. Computational Linguistics. 20(3). 498–500. 15 indexed citations
19.
Wu, Dekai. (1993). Estimating probability distributions over hypotheses with variable unification. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 790–795. 1 indexed citations
20.
Wu, Dekai. (1989). Review of Natural Language Understanding. AI Magazine. 10(1). 88–90. 1 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.

Explore authors with similar magnitude of impact

Rankless by CCL
2026