We describe a new tagging model where the states of a hidden Markov model (HMM) estimated by unsupervised learning are incorporated as the features in a maximum entropy model. Our...
: Though it is widely recognized that object-oriented methodologies are most effective in developing large scale software, it is still dif cult to apply high level computer support...
The rapid growth of geotagged social media raises new computational possibilities for investigating geographic linguistic variation. In this paper, we present a multi-level genera...
Jacob Eisenstein, Brendan O'Connor, Noah A. Smith,...
This paper presents an approach for relating informed task models and system models in the domain of safety critical interactive systems. The models, which are usually developed f...
This paper proposes a method to resolve Japanese zero pronouns by identifying their antecedents. Our method uses a probabilistic model, which is decomposed into syntactic and sema...