2020/06/15 by Yuying Ye, Ye, Yuying, Antonio Toral +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning and Data Classification #Natural Language Processing Techniques #Software Engineering Research #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.2006.08297
Accepted at the 22nd Annual Conference of the European Association for Machine Translation (EAMT 2020)
arxiv created 2020/06/15 · openalex publication_date 2020/06/15 · arxiv updated 2020/06/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This research presents a fine-grained human evaluation to compare the Transformer and recurrent approaches to neural machine translation (MT), on the translation direction English-to-Chinese. To this end, we develop an error taxonomy compliant with the Multidimensional Quality Metrics (MQM) framework that is customised to the relevant phenomena of this translation direction. We then conduct an error annotation using this customised error taxonomy on the output of state-of-the-art recurrent- and Transformer-based MT systems on a subset of WMT2019's news test set. The resulting annotation shows that, compared to the best recurrent system, the best Transformer system results in a 31% reduction of the total number of errors and it produced significantly less errors in 10 out of 22 error categories. We also note that two of the systems evaluated do not produce any error for a category that was relevant for this translation direction prior to the advent of NMT systems: Chinese classifiers.