Shallow Discourse Parsing with Maximum Entropy Model

TL;DR

This paper presents a comprehensive shallow discourse parser that integrates multiple components using maximum entropy models, effectively identifying discourse connectives, arguments, and relations from text.

Contribution

It introduces a full discourse parser pipeline that combines various subtasks with maximum entropy models and novel features, improving performance over existing methods.

Findings

Achieved significant performance improvements in discourse relation identification.

Developed a pipeline integrating connective, argument, sense, and non-explicit identifiers.

Utilized lexical and syntax features from the Penn Discourse Treebank.

Abstract

In recent years, more research has been devoted to studying the subtask of the complete shallow discourse parsing, such as indentifying discourse connective and arguments of connective. There is a need to design a full discourse parser to pull these subtasks together. So we develop a discourse parser turning the free text into discourse relations. The parser includes connective identifier, arguments identifier, sense classifier and non-explicit identifier, which connects with each other in pipeline. Each component applies the maximum entropy model with abundant lexical and syntax features extracted from the Penn Discourse Tree-bank. The head-based representation of the PDTB is adopted in the arguments identifier, which turns the problem of indentifying the arguments of discourse connective into finding the head and end of the arguments. In the non-explicit identifier, the contextual type features like words which have high frequency and can reflect the discourse relation are introduced to improve the performance of non-explicit identifier. Compared with other methods, experimental results achieve the considerable performance.