Accounting for Contiguous Multiword Expressions in Shallow Parsing
Abstract
In this paper, we focus on chunking including contiguous multiword expression recognition, namely super-chunking. In particular, we present different strategies to improve a superchunker based on Conditional Random Fields by combining it with a finite-state symbolic super-chunker driven by lexical and grammatical resources. We display a substantial gain of 7.6 points in terms of overall accuracy.