The context in which a speech-driven application is used (or conversely not used) can be an important signal for recognition engines, and for spoken interface design. Using large-...
We argue that the quality of a summary can be evaluated based on how many concepts in the original document(s) that reserved after summarization. Here, a concept refers to an abst...
In the third edition of WePS campaign we have undertaken the person name disambiguation problem referred to as a clustering task. Our aim was to make use of intrinsic link relation...
Elena Smirnova, Konstantin Avrachenkov, Brigitte T...
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...
Large repositories of source code create new challenges and opportunities for statistical machine learning. Here we first develop Sourcerer, an infrastructure for the automated c...
Erik Linstead, Paul Rigor, Sushil Krishna Bajracha...