This paper reports on the underlying IR problems encountered when indexing and searching with the Bulgarian language. For this language we propose a general light stemmer and demon...
The paper describes the treatment of some specific syntactic constructions in two treebanks of Latin according to a common set of annotation guidelines. Both projects work within ...
David Bamman, Marco Passarotti, Roberto Busa, Greg...
Syntactic reordering approaches are an effective method for handling word-order differences between source and target languages in statistical machine translation (SMT) systems. T...
Streaming validation and querying of XML documents are often based on automata for tree-like structures. We propose a new notion of streaming tree automata in order to unify the t...
When translating among languages that differ substantially in word order, machine translation (MT) systems benefit from syntactic preordering—an approach that uses features fro...