Skip to main navigation Skip to search Skip to main content

Embodiment in Multimodal Semantics: Comparing Sensory, Emotional, and Visual Features in Chinese Color Metaphors

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

17 Downloads (CityUHK Scholars)

Abstract

This study examines how sensory-motor experience, emotional valence and arousal, and visual image statistics contribute to multimodal alignment in Chinese color metaphors. Using 184 metaphorical lexemes from six basic color terms, we combined textual data from the Chinese Corpus Internet (CCI 3.0) with image sets from Baidu, embedding both with Chinese-CLIP and measuring alignment using robust pooled cosine and set-to-set Chamfer metrics. Sensory-motor ratings, especially effector exclusivity and tactile strength, correlated negatively with alignment, emotional valence showed strong positive correlations, and visual color statistics (variability, entropy) correlated positively but yielded modest generalization primarily under Chamfer. Under strict 5-fold Ridge cross-validation, emotion was the only feature group with consistently non-negative out-of-fold performance, whereas sensory ratings did not generalize. The findings indicate that affective salience and perceptual richness captured by image statistics are the principal drivers of multimodal grounding for metaphorical color words, with visual contributions emerging when alignment is evaluated many-to-many. © 2025 Association for Computational Linguistics.
Original languageEnglish
Title of host publicationProceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)
EditorsKai-Wei Chang, Ke-Han Lu, Chih-Kai Yang, Zhi-Rui Tam, Wen-Yu Chang, Chung-Che Wang
PublisherAssociation for Computational Linguistics
Pages249-257
Number of pages9
ISBN (Electronic)979-8-89176-379-1
ISBN (Print)979-8-89176-379-1
Publication statusPublished - Nov 2025
Event37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025) - National Taiwan University, Taipei City, Taiwan, China
Duration: 20 Nov 2025 → 22 Nov 2025
https://rocling2025.aclclp.org.tw/

Publication series

NameConference on Computational Linguistics and Speech Processing (ROCLING)
PublisherAssociation for Computational Linguistics

Conference

Conference37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)
PlaceTaiwan, China
CityTaipei City
Period20/11/25 → 22/11/25
Internet address

Bibliographical note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Research Keywords

  • Chinese color metaphors
  • Embodied cognition
  • Multimodal semantics
  • Text-image alignment

Publisher's Copyright Statement

  • This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Fingerprint

Dive into the research topics of 'Embodiment in Multimodal Semantics: Comparing Sensory, Emotional, and Visual Features in Chinese Color Metaphors'. Together they form a unique fingerprint.

Cite this