Analysis of discourse structure with syntactic dependencies and data-driven shift-reduce parsing
Kenji Sagae · 2009
We present an efficient approach for discourse parsing within and across sentences, where the unit of processing is an entire document, and not a single sentence.We apply shift-reduce algorithms for dependency and constituent parsing to determine syntactic dependencies for the sentences in a document, and subsequently a Rhetorical Structure Theory (RST) tree for the entire document.Our results show that our linear-time shiftreduce framework achieves high accuracy and a large improvement in efficiency compared to a state-of-the-art approach based on chart parsing with dynamic programming.