No Cover Image

Conference Paper/Proceeding/Abstract 108 views 6 downloads

Conceptual Pacts for Reference Resolution using Small, Dynamically Constructed Language Models: A Study in Puzzle Building Dialogues

Julian Hough Orcid Logo, Sina Zarrieß, Casey Kennington, David Schlangen, Massimo Poesio

The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, Pages: 3689 - 3699

Swansea University Author: Julian Hough Orcid Logo

  • 65924.VoR.pdf

    PDF | Version of Record

    © 2024 ELRA Language Resource Association: CC BY-NC 4.0

    Download (2.39MB)

Check full text

Abstract

Using Brennan and Clark’s theory of a Conceptual Pact, that when interlocutors agree on a name for an object, they are forming a temporary agreement on how to conceptualize that object, we present an extension to a simple reference resolver which simulates this process over time with different conve...

Full description

Published in: The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation
ISBN: 9782493814104
ISSN: 2522-2686
Published: ELRA and ICCL 2024
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa65924
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: Using Brennan and Clark’s theory of a Conceptual Pact, that when interlocutors agree on a name for an object, they are forming a temporary agreement on how to conceptualize that object, we present an extension to a simple reference resolver which simulates this process over time with different conversation pairs. In a puzzle construction domain, we model pacts with small language models for each referent which update during the interaction. When features from these pact models are incorporated into a simple bag-of-words reference resolver, the accuracy increases compared to using a standard pre-trained model. The model performs equally to a competitor using the same data but with exhaustive re-training after each prediction, while also being more transparent, faster and less resource-intensive. We also experiment with reducing the number of training interactions, and can still achieve reference resolution accuracies of over 80% in testing from observing a single previous interaction, over 20% higher than a pre-trained baseline. While this is a limited domain, we argue the model could be applicable to larger real-world applications in human and human-robot interaction and is an interpretable and transparent model.
Item Description: https://aclanthology.org/2024.lrec-main.327/
College: Faculty of Science and Engineering
Funders: Hough is supported by the UKRI Engineering and Physical Sciences Research Council (EPSRC) grant EP/X009343/1 ‘FLUIDITY’ and Poesio and Hough are supported by EPSRC grant EP/W001632/1 ‘ARCIDUCA’.
Start Page: 3689
End Page: 3699

Similar Items