Building Context-aware Clause Representations for Situation Entity Type Classification

TL;DR

This paper introduces a hierarchical neural network model that leverages paragraph-wide context to accurately classify clauses into situation entity types, significantly improving performance on a complex corpus.

Contribution

It presents a novel hierarchical RNN approach that jointly models clause representations with paragraph context for situation entity classification.

Findings

Achieves state-of-the-art accuracy on MASC+Wiki corpus

Approaches human-level performance in clause classification

Demonstrates effectiveness of context-aware modeling

Abstract

Capabilities to categorize a clause based on the type of situation entity (e.g., events, states and generic statements) the clause introduces to the discourse can benefit many NLP applications. Observing that the situation entity type of a clause depends on discourse functions the clause plays in a paragraph and the interpretation of discourse functions depends heavily on paragraph-wide contexts, we propose to build context-aware clause representations for predicting situation entity types of clauses. Specifically, we propose a hierarchical recurrent neural network model to read a whole paragraph at a time and jointly learn representations for all the clauses in the paragraph by extensively modeling context influences and inter-dependencies of clauses. Experimental results show that our model achieves the state-of-the-art performance for clause-level situation entity classification on the genre-rich MASC+Wiki corpus, which approaches human-level performance.