Tokenisation

Many natural language processes have some degree of preprocessing of data: tokenisation, stemming and so on. In the domain of Statisti- cal Machine Translation it has been shown that word …...

AbstractThis paper describes the University of Edinburgh’s neural machine translation systems submitted to the IWSLT 2020 open domain Japanese↔Chinese translation task. On top of commonplace techniques like tokenisation and corpus …...

AbstractWe set out to uncover the unique grammatical properties of an important yet so far under-researched type of natural language text: that of short labels typically found within structured datasets. …...