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.
BLEU
200111.9k citationsKishore Papineni, Salim Roukos et al.profile →
Peers — A (Enhanced Table)
Peers by citation overlap · career bar shows stage (early→late)
cites ·
hero ref
This map shows the geographic impact of Salim Roukos'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 Salim Roukos with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Salim Roukos more than expected).
This network shows the impact of papers produced by Salim Roukos. 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 Salim Roukos. The network helps show where Salim Roukos may publish in the future.
Co-authorship network of co-authors of Salim Roukos
This figure shows the co-authorship network connecting the top 25 collaborators of Salim Roukos.
A scholar is included among the top collaborators of Salim Roukos 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 Salim Roukos. Salim Roukos is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Fadnis, Kshitij, et al.. (2019). Heuristics for Interpretable Knowledge Graph Contextualization.. arXiv (Cornell University).3 indexed citations
6.
Lee, Young‐Suk, Bing Xiang, Bing Zhao, et al.. (2011). IBM Chinese-to-English PatentMT System for NTCIR-9.. NTCIR.1 indexed citations
7.
Florian, Radu, John F. Pitrelli, Salim Roukos, & Imed Zitouni. (2010). Improving Mention Detection Robustness to Noisy Input. Empirical Methods in Natural Language Processing. 335–345.20 indexed citations
8.
Kate, Rohit J., Xiaoqiang Luo, Siddharth Patwardhan, et al.. (2010). Learning to Predict Readability using Diverse Linguistic Features. International Conference on Computational Linguistics. 546–554.58 indexed citations
9.
Ittycheriah, Abraham & Salim Roukos. (2007). Direct Translation Model 2. North American Chapter of the Association for Computational Linguistics. 57–64.37 indexed citations
10.
Roukos, Salim. (2006). Recent results on MT evaluation in the GALE program.. IWSLT.2 indexed citations
11.
Lee, Young‐Suk & Salim Roukos. (2004). IBM spoken language translation system evaluation.. IWSLT. 39–46.7 indexed citations
Papineni, Kishore, et al.. (2002). Corpus-based comprehensive and diagnostic MT evaluation: initial Arabic, Chinese, French, and Spanish results. 132–137.22 indexed citations
14.
Franz, Martin, Jason S. McCarley, & Salim Roukos. (1998). Ad hoc and Multilingual Information Retrieval at IBM.. Text REtrieval Conference. 104–115.42 indexed citations
15.
Dharanipragada, S., Martin Franz, & Salim Roukos. (1998). Audio indexing for broadcast news. Text REtrieval Conference. 63–67.25 indexed citations
Franz, Martin & Salim Roukos. (1997). TREC-6 Ad-Hoc Retrieval.. Text REtrieval Conference. 511–516.7 indexed citations
20.
Roukos, Salim, et al.. (1996). TREC-5 Ad Hoc retrieval using K nearest-neighbors Re-scoring. Text REtrieval Conference. 415–425.4 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.