@inproceedings{george-etal-2025-using,
    title = "Using {MRS} for Semantic Representation in Task-Oriented Dialogue",
    author = "George, Denson  and
      Khalid, Baber  and
      Stone, Matthew",
    editor = "Lai, Kenneth  and
      Wein, Shira",
    booktitle = "Proceedings of the Sixth International Workshop on Designing Meaning Representations",
    month = aug,
    year = "2025",
    address = "Prague, Czechia",
    publisher = "Association for Computational Lingustics",
    url = "https://preview.aclanthology.org/tal-24-ingestion/2025.dmr-1.4/",
    pages = "30--37",
    abstract = "Task-oriented dialogue (TOD) requires capabilities such as lookahead planning, reasoning, and belief state tracking, which continue to present challenges for end-to-end methods based on large language models (LLMs). As a possible method of addressing these concerns, we are exploring the integration of structured semantic representations with planning inferences. As a first step in this project, we describe an algorithm for generating Minimal Recursion Semantics (MRS) from dependency parses, obtained from a machine learning (ML) syntactic parser, and validate its performance on a challenging cooking domain. Specifically, we compare predicate-argument relations recovered by our approach with predicate-argument relations annotated using Abstract Meaning Representation (AMR). Our system is consistent with the gold standard in 94.1{\%} of relations."
}