ValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over Centuries

Autumn Toney, Aylin Caliskan


Abstract
Word embeddings learn implicit biases from linguistic regularities captured by word co-occurrence statistics. By extending methods that quantify human-like biases in word embeddings, we introduce ValNorm, a novel intrinsic evaluation task and method to quantify the valence dimension of affect in human-rated word sets from social psychology. We apply ValNorm on static word embeddings from seven languages (Chinese, English, German, Polish, Portuguese, Spanish, and Turkish) and from historical English text spanning 200 years. ValNorm achieves consistently high accuracy in quantifying the valence of non-discriminatory, non-social group word sets. Specifically, ValNorm achieves a Pearson correlation of r=0.88 for human judgment scores of valence for 399 words collected to establish pleasantness norms in English. In contrast, we measure gender stereotypes using the same set of word embeddings and find that social biases vary across languages. Our results indicate that valence associations of non-discriminatory, non-social group words represent widely-shared associations, in seven languages and over 200 years.
Anthology ID:
2021.emnlp-main.574
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7203–7218
Language:
URL:
https://aclanthology.org/2021.emnlp-main.574
DOI:
10.18653/v1/2021.emnlp-main.574
Bibkey:
Cite (ACL):
Autumn Toney and Aylin Caliskan. 2021. ValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over Centuries. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7203–7218, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
ValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over Centuries (Toney & Caliskan, EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.574.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.574.mp4
Code
 autumntoney/ValNorm +  additional community code
Data
ConceptNet