A Parallel Multikey Quicksort Algorithm for Mining Multiword Units

In the context of word associations, multiword units (sequences of words that co-occur more often than expected by chance) are frequently used in everyday language, usually to precisely express ideas and concepts that cannot be compressed into a single word. For instance, [Bill of Rights], [swimming pool], [as well as], [in order to], [to comply with] or [to put forward] are multiword units. As a consequence, their identification is a crucial issue for applications that require a certain degree of semantic processing (e.g. machine translation, information extraction, information retrieval or summarization). In order to identify and extract multiword units, [Anonymous, 2002] has proposed a statistically-based architecture called SENTA (Software for the Extraction of N-ary Textual Associations) that retrieves, from text corpora, relevant contiguous and non-contiguous sequences of words.