@inproceedings{shun-etal-2026-diam,
title = "{DIAM}: Discourse Interaction and Addressee Modeling for {M}alaysia {H}ansard",
author = "Shun, Goh Kun and
Raj, Mohan and
Soon, Lay-Ki and
Lim, Wern Han and
Tan, Ian K. T.",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-short.19/",
pages = "240--253",
ISBN = "979-8-89176-440-8",
abstract = "Parliamentary debates are vital records of democratic processes, yet official transcripts such as the Hansard provide only a sequential account of speeches, omitting the underlying interactional structure. Although conducted in a formal setting, debates can become highly dynamic, making it difficult to determine who addresses whom and how utterances relate within the broader discussion. To address these gaps, we introduce DIAM, the first manually annotated discourse resource for the Malaysian Parliament, jointly supporting EU-level Dialogue Discourse Parsing (DDP) and multi-addressee Addressee Recognition (AR) over long, formal, unscripted spoken multi-party debate. Unlike existing DDP datasets, DIAM provides substantially longer conversations and explicit multi-addressee labels. Our benchmark experiments validate that DIAM supports both DDP and AR, while showing that existing discourse parsing methods cannot be directly applied without adaptations such as context-window strategies, and that addressee recognition is challenging for prompted LLMs, though fine-tuning a smaller model with LoRA substantially improves robustness to the large number of participants per sitting. We release DIAM and our code to facilitate future research on formal discourse parsing and addressee modeling: https://github.com/xKHUNx/DIAM"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shun-etal-2026-diam">
<titleInfo>
<title>DIAM: Discourse Interaction and Addressee Modeling for Malaysia Hansard</title>
</titleInfo>
<name type="personal">
<namePart type="given">Goh</namePart>
<namePart type="given">Kun</namePart>
<namePart type="family">Shun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohan</namePart>
<namePart type="family">Raj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lay-Ki</namePart>
<namePart type="family">Soon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wern</namePart>
<namePart type="given">Han</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="given">K</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-440-8</identifier>
</relatedItem>
<abstract>Parliamentary debates are vital records of democratic processes, yet official transcripts such as the Hansard provide only a sequential account of speeches, omitting the underlying interactional structure. Although conducted in a formal setting, debates can become highly dynamic, making it difficult to determine who addresses whom and how utterances relate within the broader discussion. To address these gaps, we introduce DIAM, the first manually annotated discourse resource for the Malaysian Parliament, jointly supporting EU-level Dialogue Discourse Parsing (DDP) and multi-addressee Addressee Recognition (AR) over long, formal, unscripted spoken multi-party debate. Unlike existing DDP datasets, DIAM provides substantially longer conversations and explicit multi-addressee labels. Our benchmark experiments validate that DIAM supports both DDP and AR, while showing that existing discourse parsing methods cannot be directly applied without adaptations such as context-window strategies, and that addressee recognition is challenging for prompted LLMs, though fine-tuning a smaller model with LoRA substantially improves robustness to the large number of participants per sitting. We release DIAM and our code to facilitate future research on formal discourse parsing and addressee modeling: https://github.com/xKHUNx/DIAM</abstract>
<identifier type="citekey">shun-etal-2026-diam</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-short.19/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>240</start>
<end>253</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DIAM: Discourse Interaction and Addressee Modeling for Malaysia Hansard
%A Shun, Goh Kun
%A Raj, Mohan
%A Soon, Lay-Ki
%A Lim, Wern Han
%A Tan, Ian K. T.
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-440-8
%F shun-etal-2026-diam
%X Parliamentary debates are vital records of democratic processes, yet official transcripts such as the Hansard provide only a sequential account of speeches, omitting the underlying interactional structure. Although conducted in a formal setting, debates can become highly dynamic, making it difficult to determine who addresses whom and how utterances relate within the broader discussion. To address these gaps, we introduce DIAM, the first manually annotated discourse resource for the Malaysian Parliament, jointly supporting EU-level Dialogue Discourse Parsing (DDP) and multi-addressee Addressee Recognition (AR) over long, formal, unscripted spoken multi-party debate. Unlike existing DDP datasets, DIAM provides substantially longer conversations and explicit multi-addressee labels. Our benchmark experiments validate that DIAM supports both DDP and AR, while showing that existing discourse parsing methods cannot be directly applied without adaptations such as context-window strategies, and that addressee recognition is challenging for prompted LLMs, though fine-tuning a smaller model with LoRA substantially improves robustness to the large number of participants per sitting. We release DIAM and our code to facilitate future research on formal discourse parsing and addressee modeling: https://github.com/xKHUNx/DIAM
%U https://aclanthology.org/2026.aacl-short.19/
%P 240-253
Markdown (Informal)
[DIAM: Discourse Interaction and Addressee Modeling for Malaysia Hansard](https://aclanthology.org/2026.aacl-short.19/) (Shun et al., AACL-IJCNLP 2026)
ACL
- Goh Kun Shun, Mohan Raj, Lay-Ki Soon, Wern Han Lim, and Ian K. T. Tan. 2026. DIAM: Discourse Interaction and Addressee Modeling for Malaysia Hansard. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 240–253, Hengqin, China. Association for Computational Linguistics.