A Collection of Pragmatic-Similarity Judgments over Spoken Dialog Utterances

Nigel G. Ward, Divette Marco
3/21/2024
cs.CL

Official code: divettemarco/PragSim (0 stars, last commit 2024-07-27).

Abstract

Automatic measures of similarity between utterances are invaluable for training speech synthesizers, evaluating machine translation, and assessing learner productions. While there exist measures for semantic similarity and prosodic similarity, there are as yet none for pragmatic similarity. To enable the training of such measures, we developed the first collection of human judgments of pragmatic similarity between utterance pairs. Each pair consisting of an utterance extracted from a recorded dialog and a re-enactment of that utterance. Re-enactments were done under various conditions designed to create a variety of degrees of similarity. Each pair was rated on a continuous scale by 6 to 9 judges. The average inter-judge correlation was as high as 0.72 for English and 0.66 for Spanish. We make this data available at https://github.com/divettemarco/PragSim .

View on arXivView PDF

Code Implementations(1)

divettemarco/PragSimOfficial100%

A Corpus of Pragmatic-Similarity Judgments over Spoken-Dialog Utterances.

00Aug 11, 20232 years ago

Similar Papers

TaskDiff: A Similarity Metric for Task-Oriented Conversations

83% match2023

Automatic Evaluation of Speaker Similarity

83% match2022

Representation of perceived prosodic similarity of conversational feedback

83% match2025

C-STS: Conditional Semantic Textual Similarity

81% match1 repo742023

Towards Precision Characterization of Communication Disorders using Models of Perceived Pragmatic Similarity

80% match2024

The More Similar, the Better? Associations between Latent Semantic Similarity and Emotional Experiences Differ across Conversation Contexts

78% match2023

Cite this paper

@article{ward2024collection,
  title  = {A Collection of Pragmatic-Similarity Judgments over Spoken Dialog Utterances},
  author = {Nigel G. Ward and Divette Marco},
  year   = {2024},
  eprint = {2403.14808},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.14808v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.14808.svg)](https://codeofpaper.com/paper/2403.14808)

Discussion