Building Context-aware Clause Representations for Situation Entity Type Classification
This work addresses a specific NLP task (clause-level situation entity classification) that can benefit applications like discourse analysis, but it is incremental as it builds on existing methods with context modeling.
The paper tackles the problem of classifying clauses by situation entity type (e.g., events, states) by proposing a hierarchical recurrent neural network model that builds context-aware representations using paragraph-wide contexts, achieving state-of-the-art performance on the MASC+Wiki corpus and approaching human-level performance.
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.