Ashok C. Popat
- Artificial Intelligence top 5%
- Computer Vision and Pattern Recognition top 10%
- Information Systems top 10%
- Signal Processing
- Computer Networks and Communications
- Co-authors
- Franz Josef OchThorsten BrantsJay B. DeanPeng XuMoshe DubinerJay PonteJakob UszkoreitYasuhisa Fujii
- Topics
- Natural Language Processing Techniques (9 papers)Handwritten Text Recognition Techniques (6 papers)Topic Modeling (5 papers)
- Journals
- Empirical Methods in Natural Language ProcessingarXiv (Cornell University)Meeting of the Association for Computational Linguistics
- Partner nations
- United StatesSwitzerlandIndia
In The Last Decade
Ashok C. Popat
14 papers receiving 479 citations
Peers
Comparison fields: 5 of 63
- Artificial Intelligence 439
- Computer Vision and Pattern Recognition 108
- Information Systems 85
- Signal Processing 34
- Computer Networks and Communications 31
Countries citing papers authored by Ashok C. Popat
This map shows the geographic impact of Ashok C. Popat'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 Ashok C. Popat with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Ashok C. Popat more than expected).
Fields of papers citing papers by Ashok C. Popat
This network shows the impact of papers produced by Ashok C. Popat. 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 Ashok C. Popat. The network helps show where Ashok C. Popat may publish in the future.
Co-authorship network of co-authors of Ashok C. Popat
This figure shows the co-authorship network connecting the top 25 collaborators of Ashok C. Popat. A scholar is included among the top collaborators of Ashok C. Popat 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 Ashok C. Popat. Ashok C. Popat is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 0 | |
| 2 | 8 | |
| 3 | General-Purpose OCR Paragraph Identification by Graph Convolution Networks | 0 |
| 4 | 8 | |
| 5 | 19 | |
| 6 | 5 | |
| 7 | 14 | |
| 8 | 6 | |
| 9 | Language-independent compound splitting with morphological operations | 33 |
| 10 | 4 | |
| 11 | Large Scale Parallel Document Mining for Machine Translation | 89 |
| 12 | 4 | |
| 13 | Large Language Models in Machine Translation | 343 |
| 14 | 8 | |
| 15 | 1 | |
| 16 | 0 | |
| 17 | 4 |
About Ashok C. Popat
Ashok C. Popat is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Signal Processing, having authored 17 papers that have together received 546 indexed citations. Recurring topics across this work include Natural Language Processing Techniques (9 papers), Handwritten Text Recognition Techniques (6 papers) and Topic Modeling (5 papers). The work is most often cited by research in Artificial Intelligence (439 citations), Computer Vision and Pattern Recognition (108 citations) and Health Informatics (6 citations). Ashok C. Popat has collaborated with scholars based in United States, Switzerland and India. Frequent co-authors include Franz Josef Och, Thorsten Brants, Jay B. Dean, Peng Xu, Moshe Dubiner, Jay Ponte, Jakob Uszkoreit, Yasuhisa Fujii, Andrew M. Dai and David Talbot. Their work appears in journals such as Empirical Methods in Natural Language Processing, arXiv (Cornell University) and Meeting of the Association for 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.