Deep Enhanced Representation for Implicit Discourse Relation Recognition

TL;DR

This paper introduces a deep model with multi-grained text representations for implicit discourse relation recognition, achieving state-of-the-art accuracy on benchmark datasets.

Contribution

It proposes a novel multi-level text representation approach combined with a deep model for improved implicit discourse relation recognition.

Findings

Achieved over 48% accuracy in 11-way classification.

Attained over 50% F1 score in 4-way classification.

Set new state-of-the-art results on the benchmark treebank.

Abstract

Implicit discourse relation recognition is a challenging task as the relation prediction without explicit connectives in discourse parsing needs understanding of text spans and cannot be easily derived from surface features from the input sentence pairs. Thus, properly representing the text is very crucial to this task. In this paper, we propose a model augmented with different grained text representations, including character, subword, word, sentence, and sentence pair levels. The proposed deeper model is evaluated on the benchmark treebank and achieves state-of-the-art accuracy with greater than 48% in 11-way and $F_1$ score greater than 50% in 4-way classifications for the first time according to our best knowledge.