... 465-472. Andrew, G. and Gao, J. 2007. Scalable training of L1-regularized log-linear models. In ICML. Charniak, E. 2000. A maximum-entropy-inspired parser. In NAACL, 132-139. Charniak, E. and ... epochs, and N is the number of training samples. 3 Evaluations From the four tasks we consider, parsing and lan-guage model adaptation are both examples of re-ranking. In these tasks, we assume ... 2007.c2007 Association for Computational Linguistics A Comparative Study of Parameter Estimation Methods for Statistical Natural Language Processing Jianfeng Gao*, Galen Andrew*, Mark Johnson*&,...