Evaluation of Chinese-English Machine Translation of Emotion-Loaded Microblog Texts: A Human Annotated Dataset for the Quality Assessment of Emotion Translation
This work addresses the problem of emotion preservation in machine translation for microblog texts, which is incremental as it applies an existing evaluation framework to a new domain.
The study evaluated how Google Translate handles emotion-loaded microblog texts, finding that about 50% of translations fail to preserve the original emotion, with errors often linked to emotion-carrying words and linguistic phenomena like polysemy and negation.
In this paper, we focus on how current Machine Translation (MT) tools perform on the translation of emotion-loaded texts by evaluating outputs from Google Translate according to a framework proposed in this paper. We propose this evaluation framework based on the Multidimensional Quality Metrics (MQM) and perform a detailed error analysis of the MT outputs. From our analysis, we observe that about 50% of the MT outputs fail to preserve the original emotion. After further analysis of the errors, we find that emotion carrying words and linguistic phenomena such as polysemous words, negation, abbreviation etc., are common causes for these translation errors.