Call for Papers

The 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL) will be held in Avignon, France on August 25-27, 2025.

The SIGDIAL venue provides a regular forum for the presentation of cutting edge research in dialogue and discourse to both academic and industry researchers, continuing a series of 25 successful previous meetings. The conference is sponsored by the SIGDIAL organization – the Special Interest Group in discourse and dialogue for ACL and ISCA.

Topics of Interest

SIGDIAL 2025 invites submissions of original research on all aspects of discourse and dialogue. We encourage formal, corpus-based, experimental, or analytical work, as well as work on implementations and applications, including but not limited to the following areas:

  • Discourse Processing: Research on rhetorical and coherence relations, discourse parsing, discourse connectives, reference resolution, event representation, and causality in narrative. This also includes work on argument mining, text quality and style, cross-lingual discourse analysis, and discourse considerations in applications like machine translation, text summarization, essay grading, question answering, and information retrieval. We particularly encourage submissions that explore discourse issues in text generated by large language models.
  • Pragmatic and Semantic Modeling: Investigations into the pragmatics and semantics of conversations, going beyond the single sentence level. This includes research on rational speech acts, conversation acts, intentions, conversational implicature, and presuppositions.
  • Dialogue Systems: Contributions related to task-oriented and open-domain dialogue systems, whether spoken, multimodal, embedded, situated, or text-based. This includes research on system components, evaluation, and applications. Specific areas of interest include knowledge representation and extraction for dialogue, state representation and tracking, policy learning, social and emotional intelligence, dialogue in virtual reality and human-robot interaction, entrainment, alignment, and priming. We also welcome work on generation for dialogue, style, voice, personality, and safety and ethics in dialogue systems.
  • LLM-Based Dialogue Technologies: Research on the use of Large Language Models (LLMs) in dialogue systems, including but not limited to areas like prompt engineering, fine-tuning for dialogue, data synthesis and augmentation for dialogue tasks, safety and ethics of LLMs in conversation, and evaluation of LLM-generated dialogue.
  • Corpora, Tools, and Methodology: Submissions focused on corpus-based and experimental work on discourse and dialogue. We encourage submissions related to annotation tools and schemes, crowdsourcing, evaluation methodologies, and corpora development.
  • Applications of Dialogue and Discourse Processing Technology: We welcome submissions showcasing innovative applications of dialogue and discourse processing technology in various domains.

Submission Types

The following submission types are expected:

  • Long Papers: 8 pages max, excluding references and appendices; +1 page in the final version. Long papers should describe substantial, original, completed, and unpublished work. Include concrete evaluation and analysis where appropriate.
  • Short Papers: 4 pages max, excluding references and appendices; +1 page in the final version. Short papers should present focused contributions, such as concise descriptions of novel ideas, negative results, or interesting application notes.
  • Demo Descriptions: 4 pages max, including references. Also a separate 1-page document for equipment requirements. Demo descriptions should clearly outline the system to be demonstrated, its functionality, and its relevance to the SIGDIAL community.

Submission Guidelines

  • Content Essential for Review: All content crucial for understanding your contribution or assessing its technical correctness should be included in the main paper, not solely in appendices. Reviewers are not obligated to review appendices.
  • Supplementary Materials: Authors are encouraged to submit supplementary materials like corpora, code, videos, or sound files to ensure reproducibility and/or enhance their submissions.
  • Multiple Submissions Policy: SIGDIAL 2025 cannot accept work that is currently under review, or has been published elsewhere, including other conferences or journals with overlapping review periods.
  • Blind Review: Long and short papers will undergo double-blind review, following ACL policies. Demo descriptions will NOT be anonymous.
  • Submission Format: All submissions must adhere to the two-column ACL format (Overleaf template and downloadable LaTeX/Word templates available). Submit electronically in PDF format.

Submission Deadlines

SIGDIAL accepts both regular submissions via the Softconf/START system and commitments of papers previously reviewed through ACL Rolling Review (ARR).

Mentoring Program

SIGDIAL 2025 offers a mentoring program to assist authors whose submissions show promise but require improvement in language or organization. Accepted papers flagged for mentoring will receive guidance from experienced SIGDIAL members to prepare their work for publication.

Best Paper Awards

SIGDIAL 2025 will recognize outstanding contributions with Best Paper Awards. All accepted papers are eligible.

Presentation Format

All accepted papers must be presented in person at the conference venue in either oral or poster sessions. Remote presentations will only be considered in exceptional circumstances (e.g., visa or health issues) with prior approval from the organizers.

Student Travel Grant

To broaden participation, SIGdial plans to support a number of selected students for paper presentations at SIGdial. Details of application for the grant will be announced soon.

SIGDIAL 2025 General Chair and Program Committee

Copyright © 2025 | MH Edition WordPress Theme by MH Themes