Traditionally, machine learning approaches for information extraction require human annotated data that can be costly and time-consuming to produce. However, in many cases, there ...
We propose a simple two-level hierarchical probability model for unsupervised word segmentation. By treating words as strings composed of morphemes/phonemes which are themselves c...
This paper presents an empirical study for improving the performance of text chunking. We focus on two issues: the problem of selecting feature spaces, and the problem of alleviat...
In this paper, we present CaptionEye/KE, a Korean to English machine translation system that is applied to a practical TV caption translation. And its experimental evaluation is p...
Seong-il Yang, Young Kil Kim, Young Ae Seo, Sung-K...
Software testing can only be formalized and quanti ed when a solid basis for test generation can be de ned. Tests are commonly generated from program source code, graphical models ...