Review on " Lexical Interference over Multi-Word Predicates: A Distributional Approach "

"Lexical Interference over Multi-Word Predicates: A Distributional Approach" is the title of the article we are discussing in this review. In fact, this document describes a new approach, of using latent variables in modeling the predicate's lexical components (LCs) in order to consider the most relevant LCs while making prediction. To begin with, a brief definition of "Multi-Word Expressions (MWEs)" which are complex lexical units and "Multi-Word Predicates (MWP)" which are informally defined as multiple words that constitutes a single predicate. MWPs form the most important sub-class of MWEs. The proposed approach to the task is complementary to most others, in which they use distributional similarity as a major component within their system. In fact, the previous works focused on improving the quality of distributional representations themselves. However, this one focuses on the integration of this type of representation to improve the identification of inference relations between MWPs. Since MWPs demonstrate varying levels of compositionality, a uniform treatment of MWPs either as fixed expressions or through head words is lacking. Instead, our approach integrates multiple lexical units contained in the predicate. The approach considers both multi-word LCs. As the method is aimed to discover the most relevant LCs, they do not attempt to analyze the MWPs in advance, but rather take an inclusive set of allowable LCs for a given predicate, allowing the model to estimate the relative weights of the LCs.  Finally, we assume that adopting an approach that combine multiple analyses would perform better than standard single-analysis methods in a large range of applications.

Lexical Interference over Multi-Word Predicates: A Distributional Approach