%0 Conference Proceedings %T A customizable, self-learning parameterized MT system: the next generation %A Su, Keh-Yih %A Chang, Jing-Shin %S Proceedings of Machine Translation Summit VII %D 1999 %8 sep 13 17 %C Singapore, Singapore %F su-chang-1999-customizable %X In this paper, the major problems of the current machine translation systems are first outlined. A new direction, highlighting the system capability to be customizable and self-learnable, is then proposed for attacking the described problems, which are mainly resulted from the very complicated characteristics of natural languages. The proposed solution adopts an unsupervised two-way training mechanism and a parameterized architecture to acquire the required statistical knowledge, such that the system can be easily adapted to different domains and various preferences of individual users. %U https://aclanthology.org/1999.mtsummit-1.29 %P 182-190