Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Standard

Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color. / Abdou, Mostafa; Kulmizev, Artur ; Hershcovich, Daniel; Frank, Stella; Pavlick, Ellie ; Søgaard, Anders.

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2021. p. 109–132.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Harvard

Abdou, M, Kulmizev, A, Hershcovich, D, Frank, S, Pavlick, E & Søgaard, A 2021, Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color. in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, pp. 109–132, 2021 Conference on Empirical Methods in Natural Language Processing, 07/11/2021. https://doi.org/10.18653/v1/2021.conll-1.9

APA

Abdou, M., Kulmizev, A., Hershcovich, D., Frank, S., Pavlick, E., & Søgaard, A. (2021). Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (pp. 109–132). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.conll-1.9

Vancouver

Abdou M, Kulmizev A, Hershcovich D, Frank S, Pavlick E, Søgaard A. Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. 2021. p. 109–132 https://doi.org/10.18653/v1/2021.conll-1.9

Author

Abdou, Mostafa ; Kulmizev, Artur ; Hershcovich, Daniel ; Frank, Stella ; Pavlick, Ellie ; Søgaard, Anders. / Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2021. pp. 109–132

Bibtex

@inproceedings{3c40de8d020f44448c22411e43c17f06,
title = "Can Language Models Encode Perceptual Structure Without Grounding?: A Case Study in Color",
abstract = "Pretrained language models have been shown to encode relational information, such as the relations between entities or concepts in knowledge-bases — (Paris, Capital, France). However, simple relations of this type can often be recovered heuristically and the extent to which models implicitly reflect topological structure that is grounded in world, such as perceptual structure, is unknown. To explore this question, we conduct a thorough case study on color. Namely, we employ a dataset of monolexemic color terms and color chips represented in CIELAB, a color space with a perceptually meaningful distance metric. Using two methods of evaluating the structural alignment of colors in this space with text-derived color term representations, we find significant correspondence. Analyzing the differences in alignment across the color spectrum, we find that warmer colors are, on average, better aligned to the perceptual color space than cooler ones, suggesting an intriguing connection to findings from recent work on efficient communication in color naming. Further analysis suggests that differences in alignment are, in part, mediated by collocationality and differences in syntactic usage, posing questions as to the relationship between color perception and usage and context.",
author = "Mostafa Abdou and Artur Kulmizev and Daniel Hershcovich and Stella Frank and Ellie Pavlick and Anders S{\o}gaard",
year = "2021",
doi = "10.18653/v1/2021.conll-1.9",
language = "English",
pages = "109–132",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
publisher = "Association for Computational Linguistics",
note = "2021 Conference on Empirical Methods in Natural Language Processing ; Conference date: 07-11-2021 Through 11-11-2021",

}

RIS

TY - GEN

T1 - Can Language Models Encode Perceptual Structure Without Grounding?

T2 - 2021 Conference on Empirical Methods in Natural Language Processing

AU - Abdou, Mostafa

AU - Kulmizev, Artur

AU - Hershcovich, Daniel

AU - Frank, Stella

AU - Pavlick, Ellie

AU - Søgaard, Anders

PY - 2021

Y1 - 2021

N2 - Pretrained language models have been shown to encode relational information, such as the relations between entities or concepts in knowledge-bases — (Paris, Capital, France). However, simple relations of this type can often be recovered heuristically and the extent to which models implicitly reflect topological structure that is grounded in world, such as perceptual structure, is unknown. To explore this question, we conduct a thorough case study on color. Namely, we employ a dataset of monolexemic color terms and color chips represented in CIELAB, a color space with a perceptually meaningful distance metric. Using two methods of evaluating the structural alignment of colors in this space with text-derived color term representations, we find significant correspondence. Analyzing the differences in alignment across the color spectrum, we find that warmer colors are, on average, better aligned to the perceptual color space than cooler ones, suggesting an intriguing connection to findings from recent work on efficient communication in color naming. Further analysis suggests that differences in alignment are, in part, mediated by collocationality and differences in syntactic usage, posing questions as to the relationship between color perception and usage and context.

AB - Pretrained language models have been shown to encode relational information, such as the relations between entities or concepts in knowledge-bases — (Paris, Capital, France). However, simple relations of this type can often be recovered heuristically and the extent to which models implicitly reflect topological structure that is grounded in world, such as perceptual structure, is unknown. To explore this question, we conduct a thorough case study on color. Namely, we employ a dataset of monolexemic color terms and color chips represented in CIELAB, a color space with a perceptually meaningful distance metric. Using two methods of evaluating the structural alignment of colors in this space with text-derived color term representations, we find significant correspondence. Analyzing the differences in alignment across the color spectrum, we find that warmer colors are, on average, better aligned to the perceptual color space than cooler ones, suggesting an intriguing connection to findings from recent work on efficient communication in color naming. Further analysis suggests that differences in alignment are, in part, mediated by collocationality and differences in syntactic usage, posing questions as to the relationship between color perception and usage and context.

U2 - 10.18653/v1/2021.conll-1.9

DO - 10.18653/v1/2021.conll-1.9

M3 - Article in proceedings

SP - 109

EP - 132

BT - Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

PB - Association for Computational Linguistics

Y2 - 7 November 2021 through 11 November 2021

ER -

ID: 299824244