The success of spoken dialog applications depends strongly on the quality of the semantic confidence measure that determines the selection of the dialog strategy. However, the sem...
We proposed a subword-based tagging for Chinese word segmentation to improve the existing character-based tagging. The subword-based tagging was implemented using the maximum entr...
The class of Linear Inversion Transduction Grammars (LITGs) is introduced, and used to induce a word alignment over a parallel corpus. We show that alignment via Stochastic Bracke...
This paper presents an extensive evaluation of five different alignments and investigates their impact on the corresponding MT system output. We introduce new measures for intrins...
Abstract--We describe some high-level approaches to estimating confidence scores for the words output by a speech recognizer. By "high-level" we mean that the proposed me...