# Structured Dialogue Discourse Parsing

Source: [Structured Dialogue Discourse Parsing](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c6e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:52:34.699Z

Authors: Ta-Chung Chi, Alexander I. Rudnicky

Published: 2023-06-26T22:51:01.000Z

## 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}.}

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Dialogue Discourse Parsing on STAC in-domain (test)](<https://www.sota2.com/research/sota/dialogue-discourse-parsing-on-stac-in-domain-test.md>): Dialogue Discourse Parsing; STAC in-domain (test); UAS: 74.4.

- [Dialogue Discourse Parsing on Molweni in-domain (test)](<https://www.sota2.com/research/sota/dialogue-discourse-parsing-on-molweni-in-domain-test.md>): Dialogue Discourse Parsing; Molweni in-domain (test); UAS: 83.5.

- [Dialogue Discourse Parsing on STAC to Molweni cross-domain (test)](<https://www.sota2.com/research/sota/dialogue-discourse-parsing-on-stac-to-molweni-cross-domain-test.md>): Dialogue Discourse Parsing; STAC to Molweni cross-domain (test); UAS: 64.5.

- [Dialogue Discourse Parsing on Molweni to STAC cross-domain (test)](<https://www.sota2.com/research/sota/dialogue-discourse-parsing-on-molweni-to-stac-cross-domain-test.md>): Dialogue Discourse Parsing; Molweni to STAC cross-domain (test); UAS: 50.6.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.15103>)

[PDF](<https://arxiv.org/pdf/2306.15103.pdf>)

[Implementation](<https://github.com/chijames/structured_dialogue_discourse_parsing>)