Shared task system description: Measuring the Compositionality of Bigrams using Statistical Methodologies
Tanmoy Chakraborty, Santanu Pal, Tapabrata Mondal, Tanik Saikh, Sivaji Bandyopadhyay · 2011
The measurement of relative compositionality of bigrams is crucial to identify Multi-word Expressions (MWEs) in Natural Language Processing (NLP) tasks. The article presents the experiments carried out as part of the participation in the shared task ‘Distributional Semantics and Compositionality (DiSCo) ’ organized as part of the DiSCo workshop in ACL-HLT 2011. The experiments deal with various collocation based statistical approaches to compute the relative compositionality of three types of bigram phrases (Adjective-Noun, Verbsubject and Verb-object combinations). The experimental results in terms of both fine-grained and coarse-grained compositionality scores have been evaluated with the human annotated gold standard data. Reasonable results have been obtained in terms of average point difference and coarse precision.