Daria Dzendzik

Learn More
In this paper we describe a semi-automatic approach to generating event extraction patterns for free texts. The algorithm is composed of four steps: we automatically extract possible events from a corpus of free documents, cluster them using dependency-based parse tree paths, validate random samples from each cluster and generate linear patterns using(More)
We show that a neural approach to the task of non-factoid answer reranking can benefit from the inclusion of tried-and-tested handcrafted features. We present a novel neural network architecture based on a combination of recurrent neural networks that are used to encode questions and answers , and a multilayer perceptron. We show how this approach can be(More)
  • 1