Abstract
Dialogue discourse parsing aims to uncover the internal structure of a multi-participant conversation by finding all the discourse links and corresponding 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).- Anthology ID:
- 2022.sigdial-1.32
- Volume:
- Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue
- Month:
- September
- Year:
- 2022
- Address:
- Edinburgh, UK
- Editors:
- Oliver Lemon, Dilek Hakkani-Tur, Junyi Jessy Li, Arash Ashrafzadeh, Daniel Hernández Garcia, Malihe Alikhani, David Vandyke, Ondřej Dušek
- Venue:
- SIGDIAL
- SIG:
- SIGDIAL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 325–335
- Language:
- URL:
- https://aclanthology.org/2022.sigdial-1.32
- DOI:
- 10.18653/v1/2022.sigdial-1.32
- Cite (ACL):
- Ta-Chung Chi and Alexander Rudnicky. 2022. Structured Dialogue Discourse Parsing. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 325–335, Edinburgh, UK. Association for Computational Linguistics.
- Cite (Informal):
- Structured Dialogue Discourse Parsing (Chi & Rudnicky, SIGDIAL 2022)
- PDF:
- https://preview.aclanthology.org/corrections-2024-07/2022.sigdial-1.32.pdf
- Code
- chijames/structured_dialogue_discourse_parsing
- Data
- Molweni