A Comparison of Approaches to Document-level Machine Translation
arXiv:2101.11040
Abstract
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.
arXiv comment10 pages, 5 tables
References in corpus (8)
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Layer Normalization
- Pointer Sentinel Mixture Models
- fairseq: A Fast, Extensible Toolkit for Sequence Modeling
- Does Neural Machine Translation Benefit from Larger Context?
- Exploiting Cross-Sentence Context for Neural Machine Translation
- The Neural Noisy Channel