Large-scale knowledge acquisition from the Web has been a popular research topic in the last five years. This talk gives an overview of our current project aiming at the acquisition of a large scale semantic network from the Web, and in the talk I explore its possible interaction with machine translation research. Particularly, I would like to focus on two topics; multilingual corpora as source of knowledge and the applications of machine translation enabled by our technology. I will discuss a framework of bilingual co-training that gives a marked improvement in accuracy of the acquired knowledge by using two corpora written in two different languages. Also, I will show our technology can enable a new type of tasks for machine translation in Web applications.