Frederik Elwert

We don’t have enough information about this author to calculate their statistics. If you think this is an error let us know.
Learn More
Recently, neural embeddings of documents have shown success in various language processing tasks. These lowdimensional and dense feature vectors of text documents capture semantic similarities better than traditional methods. However, the underlying optimization problem is non-convex and usually solved using stochastic gradient descent. Hence solutions are(More)
The advent of “distant reading” methods has created the opportunity to look at texts in a new way. But with the shift from close to distant reading, there is also a danger of loosing sight of fine-grained text structure. Like any method, distant reading methodology is not theoretically neutral, but carries a bundle of presuppositions. In this paper, a new(More)
  • 1