To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation
This work addresses the challenge of morphosyntactic divergence in machine translation for improving translation quality, though it is incremental as it analyzes existing issues without proposing new solutions.
The study compared machine and human translations using morphosyntactic divergence, finding that machine translations are more conservative with less diversity and more convergent patterns, attributed to beam search bias, and that these divergences in human translations correlate with decreased machine translation performance.
We conduct a large-scale fine-grained comparative analysis of machine translations (MT) against human translations (HT) through the lens of morphosyntactic divergence. Across three language pairs and two types of divergence defined as the structural difference between the source and the target, MT is consistently more conservative than HT, with less morphosyntactic diversity, more convergent patterns, and more one-to-one alignments. Through analysis on different decoding algorithms, we attribute this discrepancy to the use of beam search that biases MT towards more convergent patterns. This bias is most amplified when the convergent pattern appears around 50% of the time in training data. Lastly, we show that for a majority of morphosyntactic divergences, their presence in HT is correlated with decreased MT performance, presenting a greater challenge for MT systems.