Our results show that RL significantly outperforms Supervised Learning when interacting in simulation as well as for interactions with real users.

Our results show that RL significantly outperforms SL in simulation as well as in interactions with real users.

For learning presentation modality, both classifiers significantly outperform the baseline.

The results show that simulation-based RL with an environment bootstrapped from WOZ data allows learning of robust strategies which significantly outperform the strategies contained in the initial data set.

Experimental results on the NIST MT-2005 Chinese-English translation task show that our method statistically significantly outperforms the baseline systems.

1) Our tree sequence-based model significantly outperforms (p < 0.01) previous phrase-based and linguistically syntax-based methods.

Experiment results on the NIST MT-2005 Chinese-English translation task show that our method significantly outperforms Moses (Koehn et al., 2007), a state-of-the-art phrase-based SMT system, and other linguistically syntax-based methods, such as SCFG-based and STSG-based methods (Zhang et al., 2007).

The evaluation results show that: (l) The pivot approach is effective in extracting paraphrase patterns, which significantly outperforms the conventional method DIRT.

In addition, the log-linear model with the proposed feature functions significantly outperforms the conventional models.

Our experiments show that the pivot approach significantly outperforms conventional methods.