Name tagging is a critical early stage in many natural language processing pipelines. In this paper we analyze the types of errors produced by a tagger, distinguishing name classi...
We study graphical modeling in the case of stringvalued random variables. Whereas a weighted finite-state transducer can model the probabilistic relationship between two strings, ...
Abstract This paper presents an approach to designing and implementing extensible computational models for perceiving systems based on a knowledge-driven joint inference approach. ...
We define a probabilistic morphological analyzer using a data-driven approach for Syriac in order to facilitate the creation of an annotated corpus. Syriac is an under-resourced S...
Peter McClanahan, George Busby, Robbie Haertel, Kr...
This paper provides evidence that the use of more unlabeled data in semi-supervised learning can improve the performance of Natural Language Processing (NLP) tasks, such as part-o...