Little is known about why SOV order is initially preferred and then discarded or recovered. Here we present a framework for understanding these and many related word order phenomena: the diversity of dominant orders, the existence of free words orders, the need of alternative word orders and word order reversions and cycles in evolution. Under that framework, word order is regarded as a multico...

In this paper, we address the problem of combining several language models (LMs). We find that simple interpolation methods, like log-linear and linear interpolation, improve the performance but fall short of the performance of an oracle. The oracle knows the reference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word ...

This paper proposes an approach to improve statistical word alignment with the boosting method. Applying boosting to word alignment must solve two problems. The first is how to build the reference set for the training data. We propose an approach to automatically build a pseudo reference set, which can avoid manual annotation of the training set. The second is how to calculate the error rate of...

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 trainin...