We propose a high-performance cascaded hybrid model for Chinese NER. Firstly, we use Boosting, a standard and theoretically wellfounded machine learning method to combine a set of...
This paper presents a way to perform speaker adaptation for automatic speech recognition using the stream weights in a multi-stream setup, which included acoustic models for “Ar...
The goal of my dissertation research is to investigate the combination of new evidence sources for improving information retrieval on speech collections. The utility of these evid...
The goals of my dissertation are: 1) to propose a French terminology for the presentation of evaluation results of automatic summaries, 2) to identify and describe experimental va...
In word sense disambiguation, choosing the most frequent sense for an ambiguous word is a powerful heuristic. However, its usefulness is restricted by the availability of sense-an...