Fast Online Training with Frequency-Adaptive Learning Rates for Chinese Word Segmentation and New Word Detection.
ACL '12: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1(2012)
摘要
We present a joint model for Chinese word segmentation and new word detection. We present high dimensional new features, including word-based features and enriched edge (label-transition) features, for the joint modeling. As we know, training a word segmentation system on large-scale datasets is already costly. In our case, adding high dimensional new features will further slow down the training speed. To solve this problem, we propose a new training method, adaptive online gradient descent based on feature frequency information, for very fast online training of the parameters, even given large-scale datasets with high dimensional features. Compared with existing training methods, our training method is an order magnitude faster in terms of training time, and can achieve equal or even higher accuracies. The proposed fast training method is a general purpose optimization method, and it is not limited in the specific task discussed in this paper.
更多查看译文
关键词
training method,high dimensional new feature,new training method,online training,proposed fast training method,training speed,training time,large-scale datasets,general purpose optimization method,new word detection,Chinese word segmentation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络