A Comparison of Approaches to Document-level Machine Translation
This work addresses the challenge of producing coherent translations for documents, but it is incremental as it compares existing methods rather than introducing new ones.
The paper tackled the problem of document-level machine translation by systematically comparing various approaches on two benchmarks, finding that a simple back-translation method performed as well as more complex alternatives, achieving competitive results in document-level metrics and human evaluation.
Document-level machine translation conditions on surrounding sentences to produce coherent translations. There has been much recent work in this area with the introduction of custom model architectures and decoding algorithms. This paper presents a systematic comparison of selected approaches from the literature on two benchmarks for which document-level phenomena evaluation suites exist. We find that a simple method based purely on back-translating monolingual document-level data performs as well as much more elaborate alternatives, both in terms of document-level metrics as well as human evaluation.