via English-Chinese Parallel Text

We made use of parallel texts to gather train-ing and test examples for the English lexi-cal sample task. Two tracks were organized for our task. The first track used examples gathered from an LDC corpus, while the second track used examples gathered from a Web corpus. In this paper, we describe the process of gathering examples from the parallel corpora, the differences with similar tasks in previous SENSEVAL evaluations, and present the results of participating sys-tems.