France Telecom R&D Beijing Word Segmenter for Sighan Bakeoff 2006
Liu Wu, Heng Li, Yuan Dong, Nan He, Haitao Luo, Haila Wang · Meeting of the Association for Computational Linguistics · 2006
This paper presents two word segmentation (WS) systems and a named entity recognition (NER) system in France Telecom R&D Beijing. The one system of WS is for open tracks based on ngram language model and another one is for closed tracks based on maximum entropy approach. The NER system uses a hybrid algorithm based on Class-based language model and rule-based knowledge. These systems are all augmented with a set of post-processors.