Deep Enhanced Representation for Implicit Discourse Relation Recognition
This addresses the challenge of predicting discourse relations without explicit connectives in natural language processing, representing an incremental improvement in a domain-specific task.
The paper tackled the problem of implicit discourse relation recognition by proposing a model with multi-grained text representations, achieving state-of-the-art accuracy over 48% in 11-way classification and F1 score over 50% in 4-way classification.
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.