Neural RST-based Evaluation of Discourse Coherence
This work addresses discourse coherence evaluation for natural language processing applications, representing an incremental improvement over existing methods.
This paper tackles the problem of evaluating discourse coherence by incorporating Rhetorical Structure Theory (RST) features, achieving new state-of-the-art accuracy on the Grammarly Corpus for Discourse Coherence benchmark when ensembled with existing methods, and competitive accuracy with 62% fewer parameters when used alone.
This paper evaluates the utility of Rhetorical Structure Theory (RST) trees and relations in discourse coherence evaluation. We show that incorporating silver-standard RST features can increase accuracy when classifying coherence. We demonstrate this through our tree-recursive neural model, namely RST-Recursive, which takes advantage of the text's RST features produced by a state of the art RST parser. We evaluate our approach on the Grammarly Corpus for Discourse Coherence (GCDC) and show that when ensembled with the current state of the art, we can achieve the new state of the art accuracy on this benchmark. Furthermore, when deployed alone, RST-Recursive achieves competitive accuracy while having 62% fewer parameters.