Automatic Classification of Human Translation and Machine Translation: A Study from the Perspective of Lexical Diversity

TL;DR

This study demonstrates that machine translation and human translation can be distinguished systematically using lexical diversity measures, revealing important implications for translation quality evaluation.

Contribution

The paper introduces a classification approach combining trigram and BERT models to differentiate human and machine translations based on lexical diversity, highlighting its impact on evaluation metrics.

Findings

Machine translation is more accurately classified than human translation.

Lexical diversity differences explain classification performance.

Automatic metrics correlate with translation classification results.

Abstract

By using a trigram model and fine-tuning a pretrained BERT model for sequence classification, we show that machine translation and human translation can be classified with an accuracy above chance level, which suggests that machine translation and human translation are different in a systematic way. The classification accuracy of machine translation is much higher than of human translation. We show that this may be explained by the difference in lexical diversity between machine translation and human translation. If machine translation has independent patterns from human translation, automatic metrics which measure the deviation of machine translation from human translation may conflate difference with quality. Our experiment with two different types of automatic metrics shows correlation with the result of the classification task. Therefore, we suggest the difference in lexical diversity between machine translation and human translation be given more attention in machine translation evaluation.