Coordinate Structure Analysis using Local Models and CKY Algorithm

Abstract

The task of coordinate structure analysis is to identify coordinated phrases linked by a coordinator. Coordination is a major source of ambiguities in natural language and confuses even state-of-the-art syntactic parsers. In this paper, we generalize a scoring function that takes a pair of spans with a coordinator and returns a higher score for the two spans to be coordinated. During inference, our system employs this function with the CKY parsing algorithm and produces coordinate structures for a given sentence. To obtain such a function, we decompose the task into three independent subtasks and build the function based on three different neural networks for the tasks. The experimental results on English corpora demonstrate that our model achieves state-of-the-art results, ensuring that the global structure of coordination is consistent.