We present work on handling XML markup in Statistical Machine Translation (SMT). The methods we propose can be used to effectively preserve markup (for instance inline formatting or structure) and to place markup correctly in a machinetranslated segment. We evaluate our approaches with parallel data that naturally contains markup or where markup was inserted to create synthetic examples. In our...

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xi 1. OVERVIEW . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.1 The Problem Area . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.1.1 A Deceptively Simple Problem . . . ...

XML’s significance extends beyond the purpose it was originally intended to serve (document processing over the Web). As a standard and widely supported format for arbitrary data, XML delivers to any heterogeneous, distributed computer system the common lingo for data exchange — something only closed or relatively closed systems could previously assume and enforce. In addition, XML data contain...

The markup (the ratio of price to marginal cost) in Canada has risen steadily since the early 1990s suggesting a widening gap between the actual and the efficient level of output and a declining share of labour income in GDP. It exhibits non-stationary movements over the sample period 1982Q1 to 2009Q4, allowing us to identify a permanent markup shock. We provide evidence that oil price movement...