Philosophers have long been fascinated by the connection between cause and effect: are causes things we can experience or are they concepts provided by our minds? The study of causation goes back to Aristotle, but resurged with David Hume and Immanuel Kant, and is now one of the most important topics in metaphysics. Most of the recent work done in this area has attempted to place causation in a deterministic, scientific worldview. But what about the unpredictable and chancey world we actually live in: can one theory of causation cover all instances of cause and effect?1 Introduction A statistical MT system that translates (say) French sentences into English, is divided into three parts: (1) a language model (LM) that assigns a probability P(e) to any English string, (2) a translation model (TM) that assigns a probability ... Thus, while decoding is a clear-cut optimization task in which every problem instance has a right answer, it is hard to come up with good answers quickly.
|Title||:||Association for Computational Linguistics 39th Annual Meeting and 10th Conference of the European Chapter|
|Author||:||Association for Computational Linguistics. Meeting|
|Publisher||:||Morgan Kaufmann - 2001|