Translator attribution of Hongloumeng: Using entropy-based features and machine learning algorithmTranslator attribution of Hongloumeng: Using entropy-based features and machine learning algorithm

Abstract: This study utilized machine learning algorithms and entropy-based features to identify translators of two English translations of Hongloumeng, a great classical Chinese novel written in the mid-18th century. The translations under examination were completed, respectively, by David Hawkes and the Yangs (Yang Hsien-yi and Gladys Yang). Two feature sets were extracted as input for the identification of translator styles: wordform features (wordform unigrams, bigrams, and trigrams) and part-of-speech (POS) features (POS unigrams, bigrams, and trigrams). Additionally, four machine learning classifiers were tested: linear support vector machines (SVMs), linear discriminant analysis (LDA), random forest (RF), and multilayer perceptron (MLP). Analysis of feature importance and SHAP value identified the most influential features within each classifier. Results showed that LDA achieved the best performance, with 81 per cent accuracy in distinguishing between translations, showing promise for translator identification. In contrast, MLP struggled to reliably differentiate between translations, achieving only 50 per cent accuracy. Furthermore, POS features had the greatest influence in SVM and LDA, while wordform features dominated in RF. SHAP analysis revealed that Hawkes’ translation tended to exhibit higher POS unigram and lower POS trigram entropy compared to the Yangs’. This increased contribution of POS unigrams and trigrams suggests a link to explicitation differences in translation. In summary, the combination of machine learning and entropy-based stylometric features shows potential for automatic translator identification and analysis.

摘要： 本研究利用机器学习算法和基于熵的特征，识别 18 世纪中叶中国古典名著《红楼梦》两个英译本的译者。两个译本分别出自霍克思（David Hawkes）和杨宪益、戴乃迭夫妇之手。研究提取了两组特征用于识别译者风格：词形特征（词形一元、二元和三元组）和词性特征（词性一元、二元和三元组），并测试了四种机器学习分类器：线性支持向量机（SVM）、线性判别分析（LDA）、随机森林（RF）和多层感知机（MLP），再通过特征重要性和 SHAP 值分析找出各分类器中影响最大的特征。结果显示，LDA 表现最佳，区分两个译本的准确率达 81%，显示出译者识别的应用前景；相比之下，MLP 难以可靠地区分两个译本，准确率仅为 50%。此外，词性特征在 SVM 和 LDA 中影响最大，而词形特征在 RF 中占主导。SHAP 分析显示，与杨译本相比，霍译本的词性一元熵较高，词性三元熵较低。词性一元和三元特征贡献的增加，可能与两个译本在显化上的差异有关。总之，机器学习与基于熵的文体特征相结合，在译者自动识别与分析方面具有应用潜力。