Structured Dialogue Discourse Parsing

TL;DR

This paper introduces a novel structured encoding and decoding approach for dialogue discourse parsing, jointly optimizing links and relations to produce accurate discourse structures without relying on hand-crafted features.

Contribution

It presents a new method combining structured matrix encoding with a matrix-tree learning algorithm and a modified Chiu-Liu-Edmonds decoding algorithm, achieving state-of-the-art results.

Findings

Achieves new state-of-the-art F1 scores on STAC and Molweni datasets.

Joint optimization of discourse links and relations improves parsing accuracy.

Model does not rely on hand-crafted features, enhancing robustness.

Abstract

Dialogue discourse parsing aims to uncover the internal structure of a multi-participant conversation by finding all the discourse~\emph{links} and corresponding~\emph{relations}. Previous work either treats this task as a series of independent multiple-choice problems, in which the link existence and relations are decoded separately, or the encoding is restricted to only local interaction, ignoring the holistic structural information. In contrast, we propose a principled method that improves upon previous work from two perspectives: encoding and decoding. From the encoding side, we perform structured encoding on the adjacency matrix followed by the matrix-tree learning algorithm, where all discourse links and relations in the dialogue are jointly optimized based on latent tree-level distribution. From the decoding side, we perform structured inference using the modified Chiu-Liu-Edmonds algorithm, which explicitly generates the labeled multi-root non-projective spanning tree that best captures the discourse structure. In addition, unlike in previous work, we do not rely on hand-crafted features; this improves the model's robustness. Experiments show that our method achieves new state-of-the-art, surpassing the previous model by 2.3 on STAC and 1.5 on Molweni (F1 scores). \footnote{Code released at~\url{https://github.com/chijames/structured_dialogue_discourse_parsing}.}