@inproceedings{noble-ilinykh-2023-describe,
title = "Describe Me an Auklet: Generating Grounded Perceptual Category Descriptions",
author = "Noble, Bill and
Ilinykh, Nikolai",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2023.emnlp-main.580/",
doi = "10.18653/v1/2023.emnlp-main.580",
pages = "9330--9347",
abstract = "Human speakers can generate descriptions of perceptual concepts, abstracted from the instance-level. Moreover, such descriptions can be used by other speakers to learn provisional representations of those concepts. Learning and using abstract perceptual concepts is under-investigated in the language-and-vision field. The problem is also highly relevant to the field of representation learning in multi-modal NLP. In this paper, we introduce a framework for testing category-level perceptual grounding in multi-modal language models. In particular, we train separate neural networks to **generate** and **interpret** descriptions of visual categories. We measure the *communicative success* of the two models with the zero-shot classification performance of the interpretation model, which we argue is an indicator of perceptual grounding. Using this framework, we compare the performance of *prototype*- and *exemplar*-based representations. Finally, we show that communicative success exposes performance issues in the generation model, not captured by traditional intrinsic NLG evaluation metrics, and argue that these issues stem from a failure to properly ground language in vision at the category level."
}
Markdown (Informal)
[Describe Me an Auklet: Generating Grounded Perceptual Category Descriptions](https://preview.aclanthology.org/add-emnlp-2024-awards/2023.emnlp-main.580/) (Noble & Ilinykh, EMNLP 2023)
ACL