In Chinese, machine translation and local dictionaries measure moral foundations poorly; fine-tuned multilingual models and especially Llama3.1-8b do better, but still lose cultural nuance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond English: Evaluating Automated Measurement of Moral Foundations in Non-English Discourse with a Chinese Case Study
In Chinese, machine translation and local dictionaries measure moral foundations poorly; fine-tuned multilingual models and especially Llama3.1-8b do better, but still lose cultural nuance.