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.
Hybrid computing using a neural network with dynamic external memory
2016683 citationsAlex Graves, Greg Wayne et al.Natureprofile →
Citations per year, relative to Karl Moritz Hermann Karl Moritz Hermann (= 1×)
peers
Thomas E. Potok
Countries citing papers authored by Karl Moritz Hermann
Since
Specialization
Citations
This map shows the geographic impact of Karl Moritz Hermann'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 Karl Moritz Hermann with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Karl Moritz Hermann more than expected).
Fields of papers citing papers by Karl Moritz Hermann
This network shows the impact of papers produced by Karl Moritz Hermann. 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 Karl Moritz Hermann. The network helps show where Karl Moritz Hermann may publish in the future.
Co-authorship network of co-authors of Karl Moritz Hermann
This figure shows the co-authorship network connecting the top 25 collaborators of Karl Moritz Hermann.
A scholar is included among the top collaborators of Karl Moritz Hermann 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 Karl Moritz Hermann. Karl Moritz Hermann is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
16 of 16 papers shown
1.
Hill, Felix, Stephen Clark, Phil Blunsom, & Karl Moritz Hermann. (2020). Simulating Early Word Learning in Situated Connectionist Agents.. Cognitive Science.2 indexed citations
2.
Ramalho, Tiago, Tomáš Kočiský, Frederic Besse, et al.. (2018). Learning to encode spatial relations from natural language.2 indexed citations
Graves, Alex, Greg Wayne, Malcolm Reynolds, et al.. (2016). Hybrid computing using a neural network with dynamic external memory. Nature. 538(7626). 471–476.683 indexed citations breakdown →
5.
Grefenstette, Edward, Karl Moritz Hermann, Mustafa Suleyman, & Phil Blunsom. (2015). Learning to Transduce with Unbounded Memory. arXiv (Cornell University). 28. 1828–1836.73 indexed citations
Chiang, David, et al.. (2013). Parsing Graphs with Hyperedge Replacement Grammars. Oxford University Research Archive (ORA) (University of Oxford). 924–932.34 indexed citations
12.
Hermann, Karl Moritz & Phil Blunsom. (2013). The Role of Syntax in Vector Space Models of Compositional Semantics. Oxford University Research Archive (ORA) (University of Oxford). 894–904.96 indexed citations
13.
Hermann, Karl Moritz & Phil Blunsom. (2013). A Simple Model for Learning Multilingual Compositional Semantics. arXiv (Cornell University).5 indexed citations
Hermann, Karl Moritz, Phil Blunsom, & Stephen Pulman. (2012). An Unsupervised Ranking Model for Noun-Noun Compositionality. Oxford University Research Archive (ORA) (University of Oxford). 132–141.9 indexed citations
16.
Jones, Bevan, et al.. (2012). Semantics-Based Machine Translation with Hyperedge Replacement Grammars. Oxford University Research Archive (ORA) (University of Oxford). 1359–1376.65 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.