ISCA - International Speech
Communication Association


ISCApad Archive  »  2025  »  ISCApad #320  »  Events  »  Other Events  »  (2025-08-25) The 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), Avignon, France

ISCApad #320

Monday, February 10, 2025 by Chris Wellekens

3-3-33 (2025-08-25) The 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), Avignon, France
  

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

(https://www.aclweb.org/adminwiki/index.php?title=ACL_Author_Guidelines).
    Demo descriptions will NOT be anonymous.

-   Submission Format: All submissions must adhere to the two-column
    ACL format (Overleaf template (https://www.overleaf.com/project/5f64f1fb97c4c50001b60549)
    and downloadable LaTeX/Word templates
    (https://github.com/acl-org/acl-style-files) available).
    Submit electronically in PDF format.


# Submission Deadlines

SIGDIAL accepts both regular submissions via the Softconf/START system
(https://www.softconf.com/n/sigdial2025/) and commitments of papers
previously reviewed through ACL Rolling Review (ARR)
(https://aclrollingreview.org/).

Regular Submission (Softconf/START): Submission deadline is April 21,
2025 (23:59 GMT-11). The authors are allowed to update ONLY the PDF
until April 28, 2024 (23:59 GMT-11).

ACL Rolling Review (ARR): Commitment: before June 6, 2024 (23:59 GMT-11)


# 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
Conference Website: https://2025.sigdial.org


Back  Top


 Organisation  Events   Membership   Help 
 > Board  > Interspeech  > Join - renew  > Sitemap
 > Legal documents  > Workshops  > Membership directory  > Contact
 > Logos      > FAQ
       > Privacy policy

© Copyright 2025 - ISCA International Speech Communication Association - All right reserved.

Powered by ISCA