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.
Supervised Learning of Universal Sentence Representations from Natural\n Language Inference Data
20171.0k citationsAlexis Conneau, Douwe Kiela et al.arXiv (Cornell University)profile →
Citations per year, relative to Holger Schwenk Holger Schwenk (= 1×)
peers
Jason Baldridge
Countries citing papers authored by Holger Schwenk
Since
Specialization
Citations
This map shows the geographic impact of Holger Schwenk'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 Holger Schwenk with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Holger Schwenk more than expected).
This network shows the impact of papers produced by Holger Schwenk. 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 Holger Schwenk. The network helps show where Holger Schwenk may publish in the future.
Co-authorship network of co-authors of Holger Schwenk
This figure shows the co-authorship network connecting the top 25 collaborators of Holger Schwenk.
A scholar is included among the top collaborators of Holger Schwenk 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 Holger Schwenk. Holger Schwenk is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Gong, Hongyu, et al.. (2021). Multimodal and Multilingual Embeddings for Large-Scale Speech Mining. Neural Information Processing Systems. 34.17 indexed citations
Federico, Marcello, Nicola Bertoldi, Mauro Cettolo, et al.. (2014). THE MATECAT TOOL. International Conference on Computational Linguistics. 129–132.37 indexed citations
11.
Servan, Christophe, Patrik Lambert, Anthony Rousseau, Holger Schwenk, & Loïc Barrault. (2012). LIUM's SMT Machine Translation Systems for WMT 2012. SPIRE - Sciences Po Institutional REpository. 369–373.
12.
Shah, Kashif, Loïc Barrault, & Holger Schwenk. (2012). A General Framework to Weight Heterogeneous Parallel Data for Model Adaptation in Statistical MT.. Conference of the Association for Machine Translation in the Americas.1 indexed citations
13.
Zamora-Martínez, Francisco, et al.. (2010). N-gram-based machine translation enhanced with neural networks for the French-English BTEC-IWSLT'10 task.. IWSLT. 45–52.6 indexed citations
14.
Lambert, Patrik, et al.. (2010). Lium smt machine translation system for wmt 2010. SPIRE - Sciences Po Institutional REpository.3 indexed citations
15.
Schwenk, Holger & Jean Sénellart. (2009). Translation model adaptation for an Arabic/French news translation system by lightly-supervised training. SPIRE - Sciences Po Institutional REpository.21 indexed citations
16.
Schwenk, Holger. (2008). Investigations on large-scale lightly-supervised training for statistical machine translation. SPIRE - Sciences Po Institutional REpository.39 indexed citations
17.
Schwenk, Holger, Marta R. Costa‐jussà, & José A. R. Fonollosa. (2007). Smooth Bilingual N-gram Translation. SPIRE - Sciences Po Institutional REpository.26 indexed citations
18.
Schwenk, Holger & Yoshua Bengio. (1997). Training Methods for Adaptive Boosting of Neural Networks. Neural Information Processing Systems. 10. 647–653.28 indexed citations
19.
Schwenk, Holger & Maurice Milgram. (1994). Transformation Invariant Autoassociation with Application to Handwritten Character Recognition. Neural Information Processing Systems. 992–998.36 indexed citations
20.
Buzen, Jeffrey P., et al.. (1978). BEST/1 - Design of a tool for computer system capacity planning.. 447–455.10 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.