Software is developed for and in a vast number of contexts. Some software systems are small in size; some large. Some systems are developed by small teams; some large. Some projec...
Emerson R. Murphy-Hill, Gail C. Murphy, William G....
Developing better systems for document image analysis requires understanding errors, their sources, and their effects. The interactions between various processing steps are comple...
The success of Wikipedia has demonstrated the power of peer production in knowledge building. However, unlike many other examples of collective intelligence, tasks in Wikipedia ca...
We extend previous work on fully unsupervised part-of-speech tagging. Using a non-parametric version of the HMM, called the infinite HMM (iHMM), we address the problem of choosing...
Jurgen Van Gael, Andreas Vlachos, Zoubin Ghahraman...
Minimum error rate training (MERT) involves choosing parameter values for a machine translation (MT) system that maximize performance on a tuning set as measured by an automatic e...